About Translation

Study or work first, citizenship later: Italia Viva Sudamerica’s plan for Italian descendants

2026-05-11T08:00:00.000-06:00

In her article “Italia Viva Sudamerica: studio o lavoro in Italia prima della cittadinanza” for Il Globo, journalist Francesca Capelli reports on a proposal from Italia Viva Sudamerica that aims to keep citizenship by descent (ius sanguinis) without generational limits, but introduce a mandatory one‑year stay in Italy before citizenship is granted. The idea is to reduce the workload of Italian consulates in South America while encouraging young people of Italian origin to move to a country facing a serious demographic crisis.

Nicolás Fuster, the party’s South America coordinator, argues that the old system was unsustainable: many people with almost no remaining connection to Italy were obtaining citizenship, at a cost to Italian taxpayers. At the same time, Italy is aging rapidly and needs new, working‑age residents. His proposal would allow anyone of Italian descent to apply, but with a clear condition: after preparing their file (for example in Argentina, Uruguay, or Brazil) and receiving a preliminary green light from the consulate, applicants would spend one year in Italy for study or work, complete the process there, and pass a final interview in Italian.

According to Fuster, this would be a “win‑win”: consulates would be less overloaded, Italy would receive younger taxpayers from countries with a similar culture, and many of these new citizens would likely choose to stay after integrating socially and learning the language. He also stresses that supporting ius sanguinis does not exclude supporting ius soli for people born in Italy to foreign parents. However, Capelli notes that the proposal has a built‑in class filter: only those who can afford a plane ticket and a year in Italy could realistically benefit, which excludes many families in today’s Argentina.

When rules change mid‑process: Italy’s High Court and citizenship by descent ("ius sanguinis")

2026-05-01T08:00:00.000-06:00

Italy’s Supreme Court is about to decide whether the recent, stricter citizenship‑by‑descent law (“ius sanguinis”) can be applied retroactively to people who were already in the process of applying when the rules changed. The outcome will be crucial for thousands of descendants of Italian emigrants in the US, Brazil, Argentina, and elsewhere, whose paths to Italian citizenship have been suddenly blocked or thrown into uncertainty by the so‑called “Meloni law.”

In its article “Cittadinanza ius sanguinis: la Corte Suprema può ribaltare la legge”, AmeVe illustrates this through the case of Sabrina Crawford, from the San Francisco Bay Area, who spent years reconstructing her family history in Calabria to prove that her great‑grandfather never gave up Italian citizenship. Her plans, like those of many others, have been disrupted by new limits that restrict recognition to people whose parents or grandparents never renounced Italian citizenship, raising the question whether long‑standing expectations and rights can simply be switched off by decree.

The AmeVe article also points to a paradox: while Italy braces for a severe demographic decline, it is tightening access both for children of immigrants born in the country and for descendants of Italians abroad who want to reconnect with it. In other words, at the very moment when Italy needs people, it is making it harder for those already tied to the country—by birth, by blood, or by history—to be formally recognized as Italian. The Court’s ruling will say a lot about how Italy chooses to balance legal certainty, administrative control, and its relationship with the diaspora.

Italian citizenship by descent: key questions before the Italian Supreme Court

2026-04-17T08:00:00.017-06:00

A recent article on Studio Cataldi’s site explains that on 14 April 2026 the Supreme Court debated two central issues on Italian citizenship by descent (ius sanguinis). First, it must resolve a long‑running conflict on whether a child who is already a dual citizen from birth loses Italian citizenship automatically when an Italian parent later naturalises in another country while the child is still a minor. Some court decisions say yes, others say that citizenship acquired from birth should not be lost in this way, and the Court is now expected to give a single, authoritative answer.

The Court will also address how the 2025 reform applies over time. The new rules restrict recognition of ius sanguinis for people born abroad who already hold another citizenship, unless specific conditions are met. It remains unclear whether these provisions can affect situations that arose before the reform, potentially impacting rights considered “acquired” under the previous framework.

According to the article, the Supreme Court’s ruling will be a crucial step in clarifying both the historical rules on loss and transmission of citizenship and the temporal reach of the 2025 reform, providing much‑needed guidance to courts and public administrations.

If you’re affected by these changes and are gathering documents for an Italian citizenship case, feel free to get in touch about translation support. I specialize in the translation from English into Italian of official and administrative documents and can help ensure your paperwork is translated correctly and on time.

Italian citizenship reform: clearing up some legal misunderstandings

2026-04-16T08:00:00.016-06:00

A recent online article on lentepubblica.it by Italian attorney Flavia Di Pilla (Natitaliani) responds sharply to Andrea Molle’s 8 April piece in Italia Oggi (“Chi è italiano? Il legame reale pesa più della discendenza”, by Andrea Molle, Italia Oggi, April 8, 2026, see a summary in this post) about the reform of Italian citizenship. Di Pilla argues that Molle’s apparently “balanced” reading contains serious legal inaccuracies and turns a blind eye to the political interests behind the reform.

First, she notes that the Constitutional Court has not “sanctioned” a change of course on citizenship: so far there is only a press release about the 11 March hearing, not a published and reasoned judgment, so it is wrong to present the Court as having already endorsed the reform. She stresses that important constitutional challenges to article 3‑bis of Law 91/1992 (introduced by Decree‑Law 36/2025) are still pending, and that only the final written decision will clarify the Court’s position.

Second, Di Pilla reminds readers that ius sanguinis was not a casual “automatic” habit but a long‑standing, codified rule, rooted in the Civil Code of 1865 and laws from 1912 and 1992, on which institutions and individuals have relied for decades. In her view, changing such a framework through an emergency decree is constitutionally and politically problematic: the Italian Constitution allows decree‑laws only in cases of real necessity and urgency, and no convincing urgency has been shown to justify limiting rights that have existed for more than a century.

Di Pilla also highlights a geopolitical dimension Molle does not mention, alleging that pressure from the United States — concerned about South American citizens using Italian ius sanguinis to obtain an EU passport and then enter the US legally — played a role in pushing Italy towards a restrictive reform. Calling this a “correction of course in Italy’s interest”, she suggests, ignores whose interests were really being served.

Finally, Di Pilla objects to the language of “presumed descendants”: many people affected by the new rules are descendants whose link to an Italian ancestor has already been formally recognised through judgments, administrative decrees, and AIRE registrations. The real question “what does it mean to be Italian today?” is legitimate, she concludes, but it should be answered through open, democratic parliamentary debate, not via urgent decrees and press releases.

I don’t offer legal advice or citizenship consultancy, but I do work regularly on English–Italian translations for ius sanguinis citizenship applications. If you need certified translations of official papers, court decisions or other documents for an Italian citizenship application, I will be happy to help.

Italy’s citizenship debate and the risk of losing the bigger picture

2026-04-15T13:38:00.005-06:00

A recent online article by Gianni Pezzano on Daily Cases Magazine argues that the current debate on Italy’s citizenship law has become an unwelcome distraction from the real goal: strengthening the relationship between Italy and its diaspora. He recalls past scandals with fake Italian passports and notes that some agencies and applicants still treat the passport mainly as a tool for mobility or healthcare, rather than as proof of a genuine civic link.

Pezzano stresses that many descendants abroad feel rejected by the recent legal changes, often fuelled by misleading posts and commercial interests, while in Italy the same debate is tied to difficult questions about ius sanguinis, ius soli and how to integrate immigrant children born in the country. According to the article, there is no easy answer, but the author calls for more honest information, clearer communication from Italian institutions, and more responsible moderation on social media pages so that citizenship law stops being a source of anger and misunderstanding and becomes part of a broader effort to keep Italians around the world connected to Italy.

These developments also underline how important precise wording has become in citizenship matters. If you need reliable English–Italian translations for vital records, legal documents, or judgments related to ius sanguinis or other citizenship cases, I’d be happy to assist.

Italian citizenship by descent: blood, ties, and a change of course

2026-04-10T08:45:00.001-06:00

A recent commentary by Andrea Molle in Italia Oggi asks a simple but uncomfortable question: who is really Italian today? For more than a century, Italy had one of the most “generous” citizenship regimes in the world, based on ius sanguinis. In practice, this meant that millions of people, sometimes many generations and continents away, could claim Italian citizenship mainly through ancestry, with little or no real connection to Italy.

Molle argues that the latest reforms do not amount to a revolution, but to a clear change of course. Citizenship is no longer treated as an automatic inheritance; it is increasingly framed as a relationship that requires continuity, presence, and at least some degree of participation in the life of the country. The aim is to move away from producing “on paper” citizens who lack any concrete link with Italy, a system that had historical reasons but has become difficult to justify administratively and symbolically.

This shift, recently endorsed by the Constitutional Court, brings new tensions. On one side, there is the risk of weakening the historical bond with Italian communities abroad, which have long played an important cultural and economic role and have reacted harshly to these changes. On the other, Italy is trying to be coherent with what it asks of immigrants within its borders: citizenship as a real, not merely formal, belonging. In the background, Molle notes, lies the broader question that politics has largely avoided: is a genealogical link enough to be “Italian”, or do we now expect something more?

Italian citizenship by descent: the key questions before the Supreme Court

2026-04-09T10:32:00.003-06:00

A recent article by Alberto Lama on NT+ Diritto – Il Sole 24 Ore highlights why the hearing before the Sezioni Unite of the Italian Supreme Court on 14 April 2026 will be crucial for Italian citizenship by descent (ius sanguinis). In short, the Court is being asked to clarify in which cases Italian citizenship was lost in the past, and how far the 2025 reform can reach back in time.

Lama notes that the first issue concerns children born abroad as dual citizens from birth (Italian by descent and citizens of their country of birth) whose Italian parent later became a foreign citizen while they were still minors. Some decisions say these children automatically lost Italian citizenship with the parent; others say that, as duals from birth, they should keep it unless they renounce it as adults.

The second issue is the 2025 reform, which sharply restricts ius sanguinis recognition for people born abroad who already hold another citizenship, unless specific conditions are met (often, having filed a request before 28 March 2025). The key question is whether these new rules can apply to people born long before 2025, treating them as if they had never acquired Italian citizenship.

The Constitutional Court has rejected some constitutional objections to the reform (including criticism of the cut‑off date), but has not resolved all interpretation issues. It is now up to the Sezioni Unite to determine how far the 2025 rules extend in time and how they fit with the older citizenship framework.

Building a structured AI review process for human-first translation

2026-04-07T08:46:00.012-06:00

1. Human first, AI as a second pair of eyes

This article sketches how AI fits into my translation workflow, mainly for legal texts. The sequence is simple enough: I complete the translation first, then run an AI‑assisted review segment by segment, deciding which suggestions to accept and how to reshape the text. That review is still only one step in a larger process, where the translated files go through the usual QA checks for spelling, inconsistencies, numbers, tags, and glossary compliance in tools like Xbench or the QA features in memoQ or Trados.

The focus here isn’t on specific models or software brands, but on how prompt design and workflow structure make AI a usable review assistant. Prompt design turns into an ongoing job rather than a one‑off exercise: whenever I notice that something important is missing, or that a certain type of error keeps slipping through, I tweak the prompts and metainstructions.

The entire approach is based on stepwise refinement. Small adjustments over time are easier to live with than one grand design that, by its sheer mass, becomes difficult to change.

2. Why “Please review this translation” isn’t enough

When I first started experimenting with AI for legal translation work, I tried a simple “Please review this translation” prompt. In some tests I ran for this series (which I’ll describe in the next article), that bare prompt even produced results that were better than those from my more structured prompts. I don’t want to say that a generic prompt never works, because it does. It just doesn’t scale for repeated use. Generic answers tend to be too wordy, padded with comments on segments that are already correct and the reasons why they are correct. The more the model talks about everything, the harder it becomes to see the few points that really matter. What I actually need is narrower: concrete suggestions where something is off, plus brief explanations of those changes so I can quickly decide whether they’re worth adopting.

That’s why I moved to more structured prompts. I noted what went wrong with my first attempts, then started iterating on the prompts themselves with AI’s help. I would say something like, “My current metaprompt for legal projects is ABC. Can you suggest improvements?” and then keep only the parts that made sense to me. After a few rounds, I standardised on metaprompts that tell the model what to correct, what to ignore, and when to say “No change necessary.”

This makes a practical difference when you’re working in a CAT tool. I work one segment at a time, and with my current prompts I see two or three suggestions per segment, or a clear “No change necessary.” Because the instructions already say “only correct what is actually wrong,” every suggestion is at least worth considering, instead of being one more item in a long list of low‑impact refinements.

And that is the main reason a vague “Please review this translation” is not enough: not because it always fails, but because a structured prompt gives me fewer, more useful suggestions. AI review is only worth using if it doesn’t drown you in noise. Once it does, vague “smoother” edits plus over‑eager tinkering produce a long list of alternates you have to evaluate for very little benefit, so you gradually stop assessing them critically and start accepting them with little thought.

That is what the “Explain only changes” and “No change necessary” rules avoid.

3. Metainstructions: Why I bother

Sometimes it’s small, practical rules that make AI usable.

When I work on legal translations, I don’t want a generalist assistant that regurgitates commonplace English. I want something that assumes we’re in legal mode by default: contracts, pleadings, opinions. Not blog posts or LinkedIn updates. For that, I use dedicated sections (called “spaces” in Perplexity: “legal translation”, “clinical trials”, “machinery for pharmaceutical production”) as separate workbenches. Each space gives the model the rules for a specific type of translation and which authorities matter more than others.

Those instructions include the house rules where my instincts and the model’s suggestions tend to diverge. For example, I require my preferred solutions for certain source terms, like the whole cluster of cadastre / cadastral terms, which generic models mishandle. I do the same for a handful of repeat offenders in my language pairs: expressions that look deceptively straightforward but have very specific meanings, and where a translation that looks plausible (but is wrong) becomes dangerous. Some of these rules are domain‑specific; others, like typography, belong everywhere. At some point, I’ll add instructions on correct use of hyphen, en dash, and em dash (following Chicago Style) to my metaprompts. It doesn’t change the substance of a translation, but it saves me from endless low‑level clean‑up.

When I explain this to colleagues, I present Perplexity spaces as both quality and convenience aids. Quality, because each space is devoted to a specific subject, so the answers stay closer to the terminology, register, and constraints of that field. Convenience, because I can attach glossaries, links, reference documents, previous translations, and style guides once, and give niche‑specific instructions (more formal tone for legal work, more creative voice for PR or marketing) without rewriting my instructions every time. By putting these rules and references into a single metaprompt per space, I don’t have to rebuild the context from scratch. When I’m reviewing individual segments, I can use shorter structured prompts because the space already encodes the background assumptions.

This also buys me some headroom with the AI context window. I work one segment at a time in a CAT tool, and I’m not pasting lengthy instructions into every single query. That means the thread can stay coherent for longer before it starts to “forget” earlier parts of the conversation. Very long threads do sometimes lose their way, but if I notice the model drifting from the metaprompt for the space and find myself repeating instructions I already gave, that’s a sign it’s time to close the thread and start a new one.

Sometimes I add project‑specific details on top of the space, depending on the project. For short, one‑off documents, I may rely on the space alone. For longer or recurring work, I’m more likely to do some upfront preparation: extract key terminology from the source, build a glossary, and then begin the interaction with a brief note showing which glossary to use and which client preferences override the generic rules. The point is not to dump everything into one giant prompt, but to add just enough structure to ensure that the model gives me useful answers.

I keep these core prompts live in text‑expander snippets that are triggered for each segment, with a couple of small scripting shortcuts to help shuttle text between my CAT environment and the AI tool. I’ll describe the details of how I use my tools in a later article.

4. Designing the core segment review prompt

For segment‑level review, I don’t improvise the prompt every time. I use short templates because the structure of the question is always the same: give some context, show the source and target, then ask a narrowly defined question about correctness. My template looks like this: a one‑line description of the project (“In the context of a translation from US English into Italian of a real estate lease contract…”), followed by the source and target, and then a simple question such as “Is the Italian translation correct?”, plus a short list of instructions, which are the crucial part: “suggest an alternative translation only if necessary, otherwise write ‘No change necessary’”; “if you do suggest changes, explain them briefly”; and “don’t comment on the parts that remain unchanged”. At the end, I add a line about what to treat as reference (for example, authoritative Italian legal or medical sources only) and a rule to use plain text only, so I can copy and paste the output straight into my CAT tool.

What counts as “necessary” is normally the same across legal and other specialized work. The model is there to help me catch and fix genuine problems, not to polish text that is already usable and correct. Necessary changes are those that correct errors of meaning (mistranslations, omissions, unnecessary additions), errors of terminology, and then errors of form such as ungrammatical or clearly unidiomatic wording. If a suggestion doesn’t improve my translation on one of those three, it is, at best, optional. The line can shift a bit from project to project, depending on the client and the risk level, but the principle stays the same: “better” has to mean safer, clearer, or more accurate.

One thing I regularly push back against is the idea that the translation should be changed simply to mirror the structure or wording of the source. That kind of over‑rewriting is what I am trying to avoid.

The prompt doesn’t erase the problem, but it lessens it by making the model justify each proposed change instead of rewriting by default.

During a quick test I ran on a clinical study translation, the generic “Is the Italian a good translation of the English text?” prompt suggested several refinements: some were useful, others were just stylistic nudges toward more elaborate wording. The structured prompt, by contrast, gave me one compact alternative version (“disagi” and “medico responsabile dello studio” in place of weaker or vaguer options), plus a short explanation of each change—and, in other segments, a clear “No change necessary”. That is the balance I want in patient‑facing clinical texts: a handful of concrete, defensible improvements, and silence where the original is already fine.

A similar pattern shows up in a family‑law relocation clause I used for another test. With a simple prompt, another AI model quickly suggested several reasonable translations for “salvo comprovati motivi d’urgenza” and rearranged the sentence in ways that were neither wrong nor clearly better. With the structured review prompt, I asked for an alternative only if necessary, plus brief reasons. That produced one focused option (“Except for duly substantiated urgent reasons, the custodial spouse shall give the other spouse at least thirty days’ notice…”) and a concise explanation of why that wording fit actual US family‑law usage. Crucially, when I later asked Perplexity to compare its own version with the other AI’s, it opted for the wording suggested by that other AI and explained why—useful input, but still framed as a suggestion I could accept or adjust, not as a verdict.

The explicit “No change necessary” outcome is more than a cosmetic flourish. On real jobs, it makes me faster because I’m not forced to wade through commentary on segments that were already fine. A healthy percentage of “No change necessary” replies is also a sanity check on the prompt itself: it tells me the template is doing its job and not nudging the model into constant, gratuitous rewrites.

None of this means I blindly accept every suggestion that comes through. I often ask the model to defend a proposal (“Are you sure about this term?”, “Why is this better for this jurisdiction?”), or I check external sources before deciding. The template gives me a clearer, narrower stream of suggestions; it doesn’t replace my judgment. I’m sharing it here because it currently works well for my legal and medical work, and colleagues may find a similar pattern useful. It’s not a final, perfect solution, and I expect to keep adjusting it as tools and practice change.

5. Keeping the review to one prompt

I use a simple review setup: I rely on a metaprompt for everything that remains stable across projects in the same field (legal, clinical, machinery), and on one structured review prompt per segment. The metaprompt handles the background rules we’ve already seen—systems, house style, key terminology—so the per‑segment prompt can stay short. On top of that, each segment gets the same basic pattern as before: context, source and target, a short “Is this translation correct?” question, and instructions to suggest an alternative only if necessary, explain the changes briefly, and leave the rest alone.

Within that single prompt, the interactive review has a very specific job. I care mainly about meaning and terminology: catching mistranslations, omissions, or unnecessary additions, and tightening term choices where they matter. At this stage, I’m not too worried about register; either I’m already writing at an appropriate level for the document, or I make the needed adjustments before delivery. I also don’t rely on the model to check low‑level mechanical errors. Inconsistent translations, numbers, spelling, tags, and similar issues are verified and corrected using conventional translation QA tools, which are better suited to that work and don’t rewrite sentences while they’re at it.

One could design narrower AI prompts for special cases—a terminology‑focused check on a dense clause, or a quick check on a table of figures—but for my projects these are rare exceptions. Separate AI passes slow things down and give the system more opportunities to fuss with segments that were already fine. A single, well-designed review pass per segment is enough: an alternative translation, if needed, followed by a brief explanation of each change. Everything else—mechanical QA, global consistency, final register polish—belongs to other tools and other stages of the workflow.

6. Cognitive surrender, overconfidence, and simple constraints

Psychologists use the term cognitive surrender¹ for the moment you stop really evaluating AI output and simply adopt it as your own thinking. In decision‑making studies, it’s defined as accepting the system’s answer without verification, effort, or critical scrutiny: the AI’s output becomes your output. In translation, that’s when the workflow quietly slides from “human with an assistant” to “AI with a human rubber stamp on top,” especially if the model is writing the first draft of the translation and you are only skimming a fluent text under time pressure. One reason I keep AI in a review-only role is that it preserves a full round of human decision‑making before the model ever sees the text.

The Dunning–Kruger effect² looks at the same risk from a different angle. It describes a bias where people with limited knowledge in a domain overestimate their own competence, partly because they don’t know enough to see what they’re missing. Fluent AI prose can feed that bias: it makes it easy to overestimate how well we’ve really understood a text (especially in fields we don’t know too well) and how much we have genuinely contributed to the final draft, and to confuse “sounds good” with “is correct”. Cognitive surrender is one expression of that: we become overconfident in the model’s fluency, and stop asking why a given change is actually better in this instance—for this client, in this field, at this level of risk. That is why my review prompts do three things at once: they narrow the task, they explicitly allow ‘no change necessary’ and force the model to explain any change it proposes. All of this is there to keep me focused on specific suggestions, not just on a smoother‑sounding alternative.

From Ed Gandia’s writing on using AI without losing your mind,³ what stayed with me was not a specific script, but two simple ideas: be honest about what you are actually doing, and don’t over‑tinker. This means accepting that willpower is not a workflow; if I make it too easy to accept AI suggestions, I probably will. It also means resisting the urge to build elaborate, fussy review rituals “for safety” that I won’t keep up in real projects. So the rules I rely on are deliberately modest: use AI for review rather than for translation; keep the source text, my translation, and the AI’s suggestions visible; and, if something looks even slightly suspicious, slow down, ask the model to justify it or check elsewhere, and do not accept a correction until I’m satisfied it really improves meaning or terminology. I also try not to assume that silence means perfection; part of staying in charge is also noticing where no suggestion appears, but a change may still be needed. The aim is not to eliminate bias altogether, but to let the structure of my workflow do as much of the guarding as possible.

7. Workflow design, models, and practical constraints

In the review stage, once a human draft exists, the job I give to AI is very specific. I expect it to flag, correct, and briefly explain any mistranslations, terminological errors, omissions, unwarranted additions, and factual inaccuracies, with a minimum of hallucinations and in plain text so the suggestions are easy to check and apply. AI is not there to rewrite the document in its own voice, but to point out concrete problems and propose plausible fixes I can evaluate.

Everything else remains my responsibility. Structural and stylistic choices—simplifying clauses, moving phrases around, avoiding repetition or awkward sound patterns—are decisions I make myself, drawing on subject‑matter knowledge and on what will make sense to the client or end reader. The goal is that the text should read as if it had been written directly in the target language by someone well‑versed in the field, not as a slightly polished AI draft with a human name on it. AI‑assisted review is one stage between my translation and the final, non‑AI QA pass; it doesn’t replace those steps.

Because of that, the way I design the workflow matters more than the choice of any particular model. For a given project, I try to stay on one model so the behavior is predictable, but I also assume that underlying engines can change with little notice, which is why real safety comes from prompts and subject‑specific workspaces, not from loyalty to a specific AI brand. When a thread grows long and context warnings appear, I ask the system for a summary of our key decisions—terminology, register, formatting quirks, recurring corrections—and paste that into a new session so my instructions remain valid.

In the background, I try to follow the same ‘no over‑tinkering’ principle: build a simple review loop you can actually keep using, rather than a fragile ritual that only works on a perfect day.

A brief note on security: for AI‑assisted review, I use a setup with training‑time data retention disabled, avoid pasting anything that is not already covered by my NDAs and client policies, and anonymise texts where necessary. This article is about workflows and prompts; a later piece in the series will look at security practices in more detail.

8. Where structured AI review sits in your overall QA

In my workflow, AI‑assisted review is one more way of safeguarding quality, not a catch‑all safety net. It works a bit like collaborating with a trusted colleague on a translation: it helps highlight possible mistranslations, terminological slips, and omissions so I can look at them with a fresh eye, but it doesn’t replace any of the traditional checks.

Just as a formal QA step in Xbench or a CAT tool has its own job—numbers, tags, formal consistency—and just as editing by a second professional or proofreading of final copy have theirs, AI review is a separate step with a clear job to do.

Not every step will be necessary for every project, but those steps are not interchangeable. Structured prompts make AI review more focused and easier to check; they don’t turn the model into an all‑purpose editor or a substitute for final human responsibility.

1 On “cognitive surrender” and AI‑assisted decision‑making, see Gideon Nave et al., How AI is Reshaping Human Reasoning and the Rise of Cognitive Surrender (Wharton working paper, 2026), https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6097646. See also Med Kharbach, “Cognitive Surrender: How AI Is Quietly Reshaping the Way We Think” (2026), https://medkharbach.com/cognitive-surrender-how-ai-is-quietly-reshaping-the-way-we-think/. ↩

2 For a concise overview of the Dunning–Kruger effect, see Encyclopaedia Britannica, “Dunning–Kruger Effect,” https://www.britannica.com/science/Dunning-Kruger-effect. ↩

3 Ed Gandia, “How to Use AI Without Losing Your Mind” (LinkedIn, 23 Feb 2025), https://www.linkedin.com/posts/edgandia_no-new-technology-is-perfect-and-ai-is-no-activity-7299878152808353793-NMpw. ↩

Italy’s Constitutional Court upholds limits on citizenship by descent

2026-03-12T10:30:00.002-06:00

On 11 March 2026, Italy’s Constitutional Court confirmed the validity of the 2025 reform that narrowed citizenship by descent (ius sanguinis) to applicants with at least one Italian parent or grandparent, as reported by Claudio Del Frate in Corriere della Sera (article in Italian here: La corte costituzionale conferma la legge che limita lo ius sanguinis e le cittadinanze facili). The judges rejected the objections raised by the Turin court, which claimed that the new generational cap violated Article 3 of the Constitution and amounted to an implicit retroactive loss of citizenship, and they declared inadmissible the complaint based on the 1948 Universal Declaration of Human Rights.

The decision consolidates the shift introduced by Decree‑Law 36/2025 (converted into Law 74/2025), replacing the previous “infinite” bloodline approach with a two‑generation limit that focuses on closer family ties or, in some cases, a demonstrated territorial connection to Italy. This marks a clear departure from earlier practice, which had enabled many descendants of distant Italian emigrants, especially in Latin America and other large diaspora communities, to seek recognition and had generated very high volumes of applications before municipalities, consulates, and courts.

In practical terms, the pool of people who are now eligible – and therefore the number of individuals needing document translations and similar preparatory work for new applications – is likely to decrease, particularly for those relying on more remote ancestors. At the same time, people with more complex situations, or who have already started the citizenship process under the previous understanding of ius sanguinis, would be well advised to consult an Italian lawyer who specializes in this field in order to assess their position under the new framework and identify any remaining viable routes.

No, AI won’t save a weak translation: subject-matter knowledge still matters

2026-03-09T17:18:00.002-06:00

1. The “AI will cover my weak spots” story

An insidiously comforting story is doing the rounds: powerful AI has done away with the gap between specialist and non‑specialist translators. In this story, subject‑matter expertise quietly moves from a must to an afterthought: you can work with inexperienced (and conveniently cheap) translators, run everything through an MTPE process, or even exclude translators altogether and ask monolingual staff to confirm that the AI’s output looks respectable enough to ship.

The promise is simple: if the machine “knows” chemistry, finance, or property law, then the only need for a professional is as a token “human in the loop”, someone to tidy up the target language, accept most suggestions, and – most importantly – take the blame if the project goes wrong. It’s a reassuring picture for buyers under pressure to cut costs. The problem is that it bears little resemblance to how translation decisions should be taken in high‑risk situations or for specialized content.

In my workflow – the one I outlined in the first article of this series – AI only comes in after a human draft is complete. I translate first in a CAT tool, using glossaries and whatever domain knowledge I’ve built up; I revise and run proper QA.

Only then do I ask an AI assistant to review terminology, register, and style, with a strict “no change if the translation is already correct” constraint. AI can suggest alternative phrasings and highlight relevant references, but it can’t decide what’s appropriate for a specific audience, legal system, or communicative purpose. That judgment still depends on subject‑matter expertise.

2. Where AI fits

The key point of my first article was simple: AI is helpful in review because it can propose alternative translations, catch possible mistranslations, or suggest options I hadn’t thought of. As a primary translator, though, it’s dangerous: it will always produce a translation, but there is no guarantee that what it offers is correct rather than an unthinking literal translation or a smooth, fluent hallucination. That’s why I have two basic rules in my prompts for the review step: if the segment is already correct, the AI should say so and not suggest changes; and whenever it suggests a change, it should explain why.

The chemistry example from Article 1 – where “third/fourth/fifth/sixth group” became “group 13/14/15/16 elements” – worked because I knew enough about the subject to question the suggestion, and could then find evidence that it made sense in context.

This article picks up that thread. If AI is going to review our work, we still need the subject‑matter knowledge to decide when its suggestions are helpful, not merely plausible.

To give a concrete example, let’s look at a term that appears all the time in Italian property documents: catasto.

3. When the “correct” term isn’t clear

3.1 From “cadastre” to “land registry”

In Italian real‑estate documents, the words catasto and catastale crop up everywhere: contracts for the purchase, sale, or lease of property, and notarial deeds that formalize those transactions. They refer to the Italian land registry system, which records properties, their location and boundaries, and various values used for tax purposes. I see these terms in work for US clients buying or renting property in Italy, who need to understand what they’re signing. For them, the question isn’t “What is the technically correct term?”, but “What wording gives me a clear picture of what this document actually does, and whether I understand it well enough to sign it?”.

3.2 AI or MT’s usual choices

AI systems and MT engines almost always go for “cadastre” or “cadastral” when they translate catasto / catastale, terms that sound satisfyingly technical and precise. Black’s Law Dictionary, for example, defines “cadastre” as “a survey and valuation of real estate […] compiled for tax purposes”. For US lay readers, the term may look impressive, but it is opaque, because it does nothing to help them understand how a “cadastral survey” fits into the process of buying an apartment.

In real‑estate contracts and notarial deeds, this leads to prose that looks precise but fails to convey its meaning. A clause mentioning a mappa catastale may emerge as “cadastral map”, a reference to rendita catastale as “cadastral income”, and a simple check at the land office as “cadastral survey”. US buyers reading such phrases understand little: they don’t know who keeps these records, what authority they carry, or how they relate to anything they’ve seen back home.

3.3 Why I usually prefer “land registry”

When I translate for US clients dealing with Italian property, my guiding principle is simple: the client must be able to understand the meaning. I therefore generally prefer “land register” or “land registry” over “cadastre”, even if the latter looks closer to the Italian term. To a US reader, “land registry” signals “official place where property records are kept”, which is close enough conceptually and easier to understand for a non‑specialist.

So visura catastale is more helpful as something like “extract from the land registry (visura catastale)” than as a bare “cadastral search”. Mappa catastale becomes “land registry map” or “land registry plan”, depending on the document. For rendita catastale, I normally use an explanatory translation: for example, “notional property income for tax purposes (rendita catastale)”, keeping the Italian term in brackets so that any later cross‑checking with Italian documents or forms is easier.

This doesn’t mean “cadastre” is always wrong. In a different context – for instance, a technical article explaining how the Italian land registry system works – I might very well keep “cadastre” in my translation.

The important distinction is audience and purpose: translations should serve their intended function in the target context rather than mechanically mirror the source. AI can tell you that catasto often maps to “cadastre”, and it can list definitions and examples. What it cannot do is weigh up whether your specific readers are better served by that term, or by a more accessible “land registry” plus a brief explanation.

That is where professional subject‑matter knowledge and judgment come into play. AI proposes strings of words; a professional understands what those words mean, and which are appropriate for the task at hand.

3.4 “But you can always add a glossary”

A fair objection is that terminological issues can be handled through glossaries or client‑specific termbases. If a client decides that catasto is always “land registry” in their English documents, an automatic system (whether AI‑ or MT‑based) can be instructed to translate it so.

That’s helpful as far as it goes, but it doesn’t solve the underlying problem: even a mandated term still has to make sense for a specific audience and in a specific situation, and someone must know when that glossary choice no longer serves that purpose. Glossaries encode past decisions; they don’t remove the need to make new ones when the context shifts.

3.5 “Private international law” or “conflict of laws”?

The same pattern appears in other fields: AI offers something that looks legally or technically correct, but only subject‑matter knowledge tells you whether it fits the system, the audience, and the purpose of the text.

Take a standard sentence that a law firm might use to describe some services it offers:

Lo studio assiste i clienti in materia di diritto internazionale privato, ad esempio per individuare la legge applicabile ai rapporti patrimoniali tra coniugi di diversa cittadinanza.

A first draft translation might be:

The firm assists clients in matters of private international law, for example, in determining the law applicable to property relations between spouses of different nationalities.

Linguistically, there’s nothing wrong with that. An MT system or a rushed human translator could easily stop there. During review, though, I might decide to recast it as:

The firm advises clients on conflict‑of‑laws matters, for example, in determining which law applies to matrimonial property regimes between spouses of different nationalities.

Here I’m not correcting a mistranslation; I’m choosing a formulation that makes more sense for the likely readership. In an academic context, “private international law” may be the natural field label, and I would keep it as is, perhaps adding “(conflict of laws)” on first mention for US‑trained lawyers. In a law‑firm profile aimed at lay clients, though, I favor the more common “conflict of laws” and make “matrimonial property regimes” explicit.

AI can give you “private international law” and even offer “conflict of laws” as an alternative. What it cannot do is decide which label fits this specific text for this specific readership. That decision rests on your knowledge of how lawyers talk about these issues and how much conceptual scaffolding your readers already have.

4. “Truth is always a defense”: when the words are fine but the content isn’t

Sometimes the problem is not the translation but what the source text is claiming. Imagine a global corporate policy drafted at US headquarters:

Under our global communications policy, truth is always a complete defense to any defamation claim.

A correct translation might be something like:

Secondo la nostra politica globale sulle comunicazioni, la verità è sempre una difesa completa contro qualsiasi causa per diffamazione.

The translation is correct and mirrors the English source text. An inexperienced translator might sign off on it; even an experienced one, under time pressure, might not give it a thought. Yet anyone who knows a bit of Italian defamation law will feel uneasy. In the Italian legal system, even truthful statements can be defamatory if they unjustifiably harm a person’s honor or reputation. The neat “truth is always a complete defense” formula is simply incorrect in Italian law.

In a case like this, I would leave the Italian sentence as it is, because it reflects what the policy says, but I would flag it to the client. My note might say that this rule is modeled on US law and may need to be reviewed or rewritten for Italy before the policy is rolled out locally. No AI system will ever volunteer that comment: it does not know where one legal system stops and another begins.

This is another way subject‑matter expertise shows up in our work. Sometimes it means choosing “conflict of laws” over “private international law”. Sometimes it also means not changing a single word of the translation, but warning the client that the underlying claim doesn’t travel as well as they may think.

5. Domain expertise, and how to build it

“Subject‑matter expertise” might sound like a grand label, something only actual experts like lawyers or engineers can claim, but it’s more modest and more attainable than that. It’s the cumulative result of studying, gaining experience, paying attention to how people in a given field communicate among themselves, and noticing where systems and expectations differ across languages.

Part of it is exposure: reading real‑world documents rather than only parallel texts and glossaries. For real‑estate work, that might mean notarial deed templates, tax guides, and English‑language information sites for foreign buyers. For legal work, it might mean court forms, statutes, bar association materials, and law‑firm blogs in both languages. Over time, you build a mental model of who the actors are, what institutions exist, which text types are standard, and how people phrase things when they’re not writing for translators.

Another part is building your own reference system. I like to keep a corpus for each niche: links to the Italian penal, civil, and procedural codes, to their US counterparts, PDFs of relevant articles, copies of online forms, client‑side FAQs, and a log of past decisions for tricky terms. My reasoning for the choice between “cadastre” and “land registry” goes into that log. So does the decision to use “conflict‑of‑laws matters” on a particular law‑firm website, or to flag a “truth is always a defense” policy line for legal review instead of quietly normalizing it.

Expertise shows in how you use AI, rather than whether you use it at all. If you already know what the catasto is, AI can help you compare “land registry” against “cadastre” in actual usage, or suggest alternative ways of phrasing an explanation for US buyers. If you already understand the difference between libel and slander in US law and Italian diffamazione, AI can help you find references and alternative wordings for a translator’s note. Without that base, the same tool is just as likely to lure you into mistakes, because it will give you authoritative‑sounding answers that fit the wrong system.

Subject‑matter knowledge is not an optional extra that AI makes less important. It is what allows you to decide when the machine’s output is good enough, when it needs adapting for your readers, and when the problem lies not in the words but in the underlying assumptions. That is the judgment clients should expect when they hire a professional translator, and it is the part of the job no model can take over for you.

6. A practical subject‑matter checklist

I keep a simple checklist in mind when I translate with AI in the loop; at the top of that list is always to start with the purpose of the translation.[1]

1. What is the purpose of this translation?
What job does this text need to do in the target context – help a US buyer understand a contract, inform specialists, or support an academic article? The same Italian text may need to be translated differently in English for each purpose, as long as you don’t distort its legal effect and underlying meaning. An academic article on Italian property law might prefer “cadastre”, while the translation of a deed for a US buyer won’t.

2. Who will actually read it?
Are we translating for lay US property buyers, Italian notaries, in‑house counsel, or EU policy staff? Your choice between a specific technical term and an explanatory phrase depends on this. A term that works for a specialist audience may be pure noise for someone who just wants to know what happens if the roof leaks.

3. What does your audience need to do with it?
Do they need to sign it, follow it, file it, or simply be informed? Someone who has to sign a notarial deed needs more than a term that looks technically correct; they need a fair chance of understanding what they’re committing to. For a background briefing, on the other hand, a more technical label might be perfectly acceptable if it’s explained once.

4. Would this term mean anything to them?
If you showed your reader the term on its own, would they recognize it and know what it involves? If not, you need a better solution, possibly with the original term in brackets on first occurrence. That AI can define the word doesn’t mean your readers will understand it when they see it in a contract.

5. Is there a real‑world equivalent in the target system?
Does your audience’s country or legal system have an institution that plays a similar role, even if the match isn’t perfect? In many English‑language contexts, “land registry” is closer to what a US buyer expects than “cadastre”, even if the Italian catasto is not identical to any US office. The goal is a responsible approximation, not a one‑to‑one mirage.

6. How much risk is involved in this choice?
If a non‑specialist misunderstands this term, are we looking at mild confusion, or potential legal or financial consequences? The higher the risk, the less the translation can afford to hide behind a dictionary gloss or an AI suggestion that “sounds legal”. In regulated or high‑stakes domains, “defensible but potentially misleading or unclear” is often the worst of both worlds.

7. How does this interact with your existing terminology?
Will accepting the AI’s suggestion break consistency with your glossaries or previous work for this client or domain? Sometimes the fix is as simple as giving the AI a client glossary or termbase so that it stops inventing alternatives. But a glossary doesn’t remove the need for judgment; it just moves it upstream, to when terms are chosen and to the cases where the approved term doesn’t fit the purpose. And when a client questions an inconsistency, AI will not defend your choices for you.

8. What role do you want AI to play?
Are you asking AI to propose synonyms, retrieve definitions, check consistency, or simply sanity‑check a decision you’ve already made? If you catch yourself expecting it to decide which option fits your purpose and audience, that’s a red flag. In my workflow, once I’m clear on these questions, AI is there to challenge me and to point out blind spots, not to choose the target term on my behalf.

If you can’t answer several of these questions with reasonable confidence, the problem isn’t your review prompt or your choice of AI tool. It’s that you don’t yet understand the subject – or the translation’s purpose – well enough to delegate any part of the decision‑making. That’s not a criticism; it’s a signal about where to invest your next hours of research.

7. Where this leaves human + AI workflows

Taken together, the picture is less dramatic than the “AI has done away with the gap” story, and much more useful. AI can help us check consistency, spot alternative phrasings, and compare how terms are used across sources, but it cannot decide which solution fits a given purpose, audience, and level of risk. That part depends on subject‑matter knowledge and on the professional responsibility you can’t outsource to a model.

In the workflow I described in Article 1, what matters most is when you use AI. I translate first, making concrete decisions about terms like catasto based on who will read the text and what they need to do with it; then I let AI challenge those decisions under strict “no unnecessary changes, always explain why” constraints. Used this way, AI doesn’t level the field between strong and weak translators; it widens the gap, because the more you know about your subject, the more the tool can help you.

The next articles in this series will pick up from here and get more practical. I’ll look at how to design prompts that reflect your existing decisions and glossaries, and at how to integrate AI review into a broader toolbench that includes CAT tools, QA checks, and your own reference material. The core principle, however, will stay the same: AI can speed up parts of the process, but it cannot think through our choices or take responsibility for them. That’s still our job – and it’s where a professional translator’s value lies.

Notes

[1] Vermeer and Reiss’ Skopos theory reminds us that the purpose of the translation should guide our choices, and Andrew Chesterman’s Memes of Translation is still one of the clearest accounts of how ideas like this shape everyday practice.

Why I use AI for review, but not for translation (most of the time)

2026-03-05T18:31:00.014-07:00

This is the opening article in a series about how I combine human translation with controlled AI review. I’m writing mainly for translators who don’t want to outsource their judgment to a black‑box tool, and for organizations that care more about process and reliability than “magic prompts”.

In this first article, I want to answer a simple question before we dive into scripts and workflows: why do I use AI almost only for review, not to produce the first draft?

My baseline: human first, tools as helpers

On a typical project, I follow a familiar workflow:

I translate segment by segment in a CAT tool (usually Trados or memoQ).
I draw on glossaries I’ve built over the years, and sometimes glossaries provided by the client.
I revise each segment in the CAT tool as I go.
At the end, I run a QA pass, usually with Xbench, to catch inconsistent translations and errors in spelling, numbers, tags, terminology, and similar issues.

AI comes in after the first human draft. I send selected segments or paragraphs to an AI assistant (Perplexity Pro) with a narrow brief: check terminology and register, suggest improvements where needed, but say “no change necessary” if the translation is already correct. I’m not asking it to invent content; I’m asking it to challenge my choices.

That distinction—AI for drafting vs. AI for review—is the point of this article.

What AI is actually doing to translation work

AI and MT have already taken over the bottom of the translation market and are chewing through the middle. Much low‑end work has either disappeared or returned as “human in the loop” post‑editing, often at rates that don’t reflect the risk.

At the same time, many translators are using the same tools to improve quality and consistency, especially on specialized material. There’s a big difference between:

“Let’s have AI churn out a first draft and you do a quick skim”, and
“You produce a solid human draft, then use AI to check terminology and style in a structured way.”

This series is about the second scenario.

Where AI actually helps in review

In one recent project, I translated Italian‑into‑English engineering and chemistry course descriptions written in the 1980s, for an application being submitted now. The source reflected older terminology; the translation had to match current usage.

One syllabus section included:

Parte descrittiva: idrogeno; metalli alcalini; elementi del terzo gruppo; elementi del quarto gruppo; elementi del quinto gruppo; elementi del sesto gruppo; alogeni; elementi di transizione; chimica organica.

My first English draft was:

Descriptive section: Hydrogen; alkali metals; third‑group elements; fourth‑group elements; fifth‑group elements; sixth‑group elements; halogens; transition elements; organic chemistry.

With a “check and only suggest changes if needed” prompt, AI proposed:

Descriptive section: Hydrogen; alkali metals; group 13 elements; group 14 elements; group 15 elements; group 16 elements; halogens; transition elements; organic chemistry.

On the face of it, that’s a bold change: terzo gruppo becomes “group 13”. If the Italian says “third group”, “group 3” is the obvious reading.

The key step was to look at the surrounding content. The same section goes on to discuss:

third‑group elements and the industrial production of aluminium
fourth‑group elements, focusing on carbon and silicon
fifth‑group elements, then nitrogen, phosphorus, nitric and phosphoric acids, fertilizers
sixth‑group elements, then oxygen, sulfur, sulfur oxides, sulfuric acid

Aligned with modern periodic‑table families, this clearly follows an older main‑group convention: aluminium family → Group 13, carbon/silicon → Group 14, nitrogen/phosphorus → Group 15, oxygen/sulfur → Group 16.

In this context, “group 13/14/15/16 elements” is the right modern phrasing in English. AI’s suggestion pointed in the correct direction, but I still had to read the syllabus, know the chemistry, and confirm the mapping against current references. The useful part was speed: Perplexity also surfaced relevant reference material, so checking the group numbers took minutes rather than a small research session.

A second example from the same materials is simpler. One course title read Automazione e Regolazione. My first draft was “Automation and Regulation”, which is literal but slightly off in engineering. When I asked AI to review the title in context (“US English, engineering university course titles”), it suggested “Automation and Control” instead and noted that in control engineering regolazione here is about automatic control systems and control theory, and “Control” is the standard term.

It’s a small change, but it makes the course title sound like something an engineer would actually write today, not a direct echo of the Italian.

Both examples show the pattern. I draft the translation, then use AI to ask: “Is this how a current English‑language textbook or course catalog would phrase it?” Sometimes the answer is “no change necessary”, which is helpful in itself. Sometimes I get a better term (“Control” instead of “Regulation”). Sometimes I get a suggestion that only holds up once you check it against the underlying discipline. In all cases, I decide what goes into the final draft; AI just helps me interrogate my own work.

Why I don’t use AI for the first draft

If AI can do all that in review, why not let it produce the draft and just “fix things up” afterwards?

I resist that for a few reasons:

Hallucinations and smooth nonsense
Modern systems can produce fluent, plausible text, but they’re not good at signalling uncertainty. In technical or academic work, that’s risky. I prefer to start from a translation whose meaning I know, rather than from a confident text that may be wrong in subtle ways.

Terminology drift and inconsistency
Over a long document, AI can drift in terminology, use different phrases for the same concept, or shift definitions. Cleaning that up after the fact is often harder than keeping terms under control while writing.

The “expert as janitor” problem
“We’ll have AI do the first draft and you just review it” usually means “take on the liability of spotting errors, but at a discount”. An AI‑first draft often has a higher error rate than a careful human draft, and responsible review takes time. It’s not quick; it’s just different work.

Control over voice and argument
In some content, structure and tone are part of the meaning. If I let a tool produce the first version, I still have to rebuild the argument, nuance, and hedging afterwards.

In short: I’d rather think through the text once as I write it, then use AI to check and refine, than spend the same or more time trying to infer what a system “meant”.

How I keep AI in its lane

A lot of this comes down to how you frame the task.

For review, my prompts usually say, in effect:

Focus on terminology, register, and clarity.
Suggest changes only where something is incorrect, unclear, or clearly suboptimal.
If the translation is already correct, respond with “No change necessary.”
If you’re uncertain about a term, say so and give alternatives.

This reduces noise: I don’t want the tool rewriting clean sentences. It also makes it clearer which suggestions are genuine corrections vs. preferences.

There are times when I “spar” with the system. It suggests something that doesn’t quite fit; I push back, adjust, and sometimes end up with a third option that’s better than either my original or its first attempt. But the direction is clear: I have the brief and the responsibility. AI is there to catch blind spots and propose options.

I’ll dig into prompt design in a later article. For now, the important point is that the prompt mirrors the workflow: human first, AI second, human last.

Practical takeaway (for colleagues and clients)

If you’re a translator, before asking “How can I get AI to translate this for me?”, try “How could AI help me review my own translation more effectively?” Start human, then use the tool to:

check that your terminology matches current usage in the field,
challenge titles, headings, and boilerplate that may have aged, and
reach reference material quickly when something looks like an old convention.

If you’re a client or project manager, the safer setup for serious content is still human translation plus AI‑assisted review, not AI‑first with “quick human post‑editing”. You want someone who understands both the domain and the tools, and who uses AI to support their judgment, not replace it.

In the next article, I’ll look at why subject‑matter expertise is still non‑negotiable in an AI world. Without that, AI review quickly turns into curating style instead of checking meaning.

How I use AI to clean up OCR output

2026-02-28T17:09:00.007-07:00

OCR tools such as ABBYY FineReader PDF, Adobe Acrobat (Scan & OCR), Readiris 17, and OmniPage are widely used to convert scanned pages into editable text. They handle the heavy lifting of recognition, but their output almost always contains familiar OCR artefacts: split words at line breaks, strange spacing, and character substitutions like “l” for “1” or “rn” for “m.”

AI tools, like Perplexity Pro, ChatGPT and Claude, can step in as a targeted post‑processing layer. Instead of the time-consuming process of checking each suspicious character in your OCR tool or word processor, you let the AI work at sentence and paragraph level, using context to decide what the text was meant to say while keeping the content intact.

Suggested workflow

Run OCR and export text
Use your preferred OCR tool to recognize the document and export the result as plain text, Markdown, or Word. Avoid exporting to formats that hide extra formatting (e.g. heavily styled PDFs), because you want clean, editable text for the AI.
Send chunks to the AI with a focused prompt
Work in sections (for example, 5–10 pages at a time). Prompt example:
“This text comes from OCR and contains typical OCR artefacts. Correct broken words, spacing, punctuation, and capitalization, but preserve all content, line breaks, and headings as much as possible. Do not summarize or omit anything.”
Review against the scan in a side‑by‑side view
Open the scanned PDF/image on one side of your screen and the AI‑corrected text on the other. Check critical areas: headings, numbers, tables, and domain‑specific terms (e.g. drug names, legal references, codes). Correct any terminology the AI “normalized” incorrectly.
Use a diff tool between raw OCR and AI output
Run a text diff between the raw OCR file and the AI‑corrected version. This helps you see exactly what changed, confirm that nothing was dropped, and quickly scan for any over‑confident “corrections” you don’t want.
Automate for larger volumes
For recurring projects, you can script the process: batch‑export from your OCR tool, segment the text, send each chunk to the AI via API, then reassemble the cleaned text. Human effort can then be reserved for spot‑checking and final QA instead of first‑pass cleanup.

By combining a robust OCR engine with an AI cleanup step, you move from “barely readable extraction” to text that is reliable enough for translation, further editing, or long‑term archiving, without spending hours fixing the same types of errors by hand.

Translation Notes: “Director”

2026-01-27T16:35:00.000-07:00

Translating “Director” into Italian in legal, business, and financial contexts is less straightforward than it looks.

Meanings of “Director”

In English corporate practice, a director is usually a member of the board, i.e., part of the company’s governing organ. In job titles like “Finance Director” or “Marketing Director”, however, “director” often labels a senior manager heading a function, not necessarily a board member.

Italian translations

For Italian joint stock companies (“Società per Azioni”, or S.p.A.) and limited liability companies (“Società a responsabilità limitata”, or S.r.l.), the functional equivalent of a board “director” is an amministratore (or membro del consiglio di amministrazione). In this sense, director and amministratore both indicate a person who takes part in management and decision‑making at organ level.

Within the board, titles such as “managing director” or “executive director” are commonly rendered as amministratore delegato (or “AD”), who is both an amministratore (board member) and the top executive charged with day‑to‑day management. In current Italian practice, the amministratore delegato is often referred to by the English acronym “CEO”.

By contrast, direttore in today’s corporate Italian typically indicates a high‑ranking employee: direttore generale, direttore finanziario, direttore commerciale, etc. Modern legal drafting tends to reserve amministratore for members of the board and direttore for management roles within the organizational chart.

False friends and traps

The main trap is translating every “director” as direttore. When “director” refers to a board member, the correct Italian is amministratore or membro del consiglio di amministrazione, not direttore. A direttore generale is usually a top manager reporting to the board, not one of its members.

Rule of thumb

If the person sits on the board → amministratore / membro del consiglio di amministrazione.
If it’s a functional job title → direttore (+ area: finanziario, marketing, ecc.).

Italian Citizenship Law Update: Stricter Rules for Descendants Abroad

2025-03-29T13:37:00.001-06:00

The new rules will impact individuals applying or planning to apply for Italian citizenship through their Italian ancestry (known as "ius sanguinis"), as well as professionals (like translators) who assist with these applications.

The decree-law approved today stipulates that Italian descendants born abroad will automatically be citizens for only two generations: those with at least one parent or grandparent born in Italy will be citizens from birth. In the second phase, a bill also approved today introduces further and more substantial changes to the citizenship law. Notably, citizens born and residing abroad must maintain real ties with our country over time, exercising their citizenship rights and duties at least once every twenty-five years.

The reform is completed by a second bill that revises the procedures for recognizing citizenship. Going forward, residents abroad will no longer apply through consulates but will instead use a special centralized office at the Ministry of Foreign Affairs. A transition period of about one year is planned for organizing this office. The goal is to streamline procedures, achieving clear economies of scale. Consulates will focus on serving existing citizens rather than processing new citizenship applications. Additionally, the provision includes measures to enhance and modernize service delivery: legalizations, civil registry services, passports, and travel identity cards. Organizational measures are also planned to ensure the Ministry of Foreign Affairs increasingly serves citizens and businesses.

From a press release published on March 28, 2025 by the Italian Ministry of Foreign Affairs.

Try Perplexity Pro free for one month

2024-11-27T12:57:00.007-07:00

I have a couple of discount codes to try Perplexity AI free for one month. I’ll give them to the first two persons who’ll ask for them by sending me an email from this blog (see on the right) or in Linkedin.

Perplexity AI, Your Translation Research, Terminology and Review Assistant

2024-11-23T10:29:00.001-07:00

I’ve just added to the “Other Presentations” page of this blog the presentation I recently gave on Perplexity AI at the AI in Translation Summit.

What is Perplexity AI, and how can it help us?

A Perplexity query

Perplexity AI is an innovative search tool combining web searching with language models for concise, contextual answers.

Unlike traditional search engines, it gives conversational answers with citations, and, unlike AI tools like ChatGPT, it offers real-time web searching, with several advantages for translators, such as access to current information on specialized topics, helping us understand the context of our projects. It also helps in terminology research for domain-specific terms.

Perplexity can verify short translated segments by cross-referencing our translations against its search results, to identify potential errors, and the paid version has enhanced privacy features, allowing secure upload of confidential documents.

Perplexity helps gather contextual information and find references for our translations.

It provides us with detailed overviews of complex topics.

For example, if we are translating a legal document about international child custody laws, we can ask Perplexity for a summary with a query like "Summarize the differences between child custody laws in Italy and the US", and the system compiles a concise summary from various sources.

Perplexity incorporates contextual information in its responses; this means that we can ask follow-up questions to dig deeper without repeating the background. For example, we might inquire what weight is given to children's wishes in custody decisions.

Perplexity provides citations, which allow us to verify the sources it finds for us; but remember that we should always cross-check crucial information. The best use for this system is as a starting point to guide our research, not as the sole source of information.

By leveraging Perplexity's real-time search and summarization functions, we can find better information on complex subjects, speeding up our background research.

While Perplexity is a powerful tool, it's important to remember that, like all AI models, it may occasionally produce errors and hallucinations: it’s a helpful assistant, not a replacement for our expertise.

Los Angeles Review of Books and Yefe Nof Translation Residency

2024-08-21T14:48:00.000-06:00

The Los Angeles Review of Books and Yefe Nof present the third year of their joint translation residency. Applications are open to emerging translators who have not yet published a book-length project.

For more details, see the original announcement.

Italian and English installable or online dictionaries

2023-07-05T12:41:00.003-06:00

I first wrote about the Italian bilingual and monolingual dictionaries available online some eighteen years ago. Since, however, such links are liable to change, with old sites disappearing and new ones taking their place, below is an up-to-date list of sites that offer English-Italian, Italian monolingual, and other Italian bilingual dictionaries.

Picchi’s English-Italian dictionary (published by Hoepli) is available for free from La Repubblica website: Dizionari - La Repubblica. The same site also offers the Grande Dizionario di Italiano Hoepli and Hoepli’s Dizionario dei sinonimi.
The current incarnation of the excellent Sansoni English-Italian dictionary (published by Rizzoli) is available online at the Corriere della Sera website: Dizionari e Traduttori - Corriere della Sera. The same web page also offers several other Italian monolingual dictionaries, like the Dizionario dei modi di dire and a Dizionario di citazioni, and Italian-Spanish, Italian-French and Italian-German and Latin-Italian bilingual dictionaries.
The venerable Hazon English-Italian dictionary is available from the Garzanti website: Garzanti Linguistica, where you can also find Garzanti’s Italian monolingual dictionary and an Italian-French bilingual dictionary.
The English-Italian bilingual dictionary I’m currently using most often is Ragazzini’s. You can subscribe to it on Zanichelli’s site (Dizionari online Zanichelli). From the same site you can subscribe to several other dictionaries, including Zingarelli (Italian monolingual), several specialized English-Italian bilingual dictionaries, and other bilingual dictionaries including Italian-Spanish, Italian-French, Italian-German, Italian-Russian, Italian-Arabic, Italian-Modern Greek, Italian-Chinese and Italian Japanese.
Oxford-Paravia Concise English-Italian dictionary is available as a (paid) subscription from the MobySystems website.
WordReference.com offers free access to a useful English-Italian dictionary, as well as several other online dictionaries.
The eLexico.com website offers a wide range of bilingual and monolingual dictionaries, either via online subscriptions (generally more expensive than those available from Zanichelli), downloadable installable dictionaries, or both things combined. Among the dictionaries downloadable from eLexico.com are Picchi, Sansoni, and many others; unfortunately, the excellent Italian monolingual Devoto-Oli is no longer available for individual subscription, though it is offered for multi-user subscriptions.
While the bilingual dictionaries offered by eLexico include Marolli’s Grande Dizionario Tecnico Inglese, it is cheaper to buy it as a Windows app from this link.
Lexicool.com lets the user search many dictionaries. You can find Italian-English bilingual dictionaries, as well as many other linguistical resources.
The Treccani website offers access to the Enciclopedia italiana online, to the Italian language Vocabolario, and to a good Italian synonyms dictionary.
Il Nuovo De Mauro is a very useful Italian monolingual dictionary and can be consulted for free online.
Francesco Urzì’s indispensable Dizionario delle Combinazioni Lessicali is available as a (paid) online resource.
Finally, for those of us who try to resist the tide of useless, redundant (and often misleading and incorrect) anglicisms in Italian, Antonio Zoppetti offers il dizionario delle Alternative agli Anglicismi, significati e sinonimi in italiano.

How to access Microsoft terminology now that Microsoft shut down its Language Portal

2023-07-03T18:37:00.002-06:00

On June 30, Microsoft closed the Microsoft Language Portal. For at least a few weeks before that, a message appeared on the Portal, with links from which the users could download Microsoft Terminology and Style Guides.

Those links disappeared with the Portal, but it is still possible to download the style guides and access both terminology and the UI strings:

See below:

The interface provided to search the terminology and UI strings is Microsoft Power BI, a “unified, scalable platform for self-service and enterprise business intelligence (BI)”.

Whether the access to terminology and UI strings through Power BI is temporary or permanent is unknown.

Subscribers to MSDN platforms used to be able to download all UI strings and terminology. I don’t know if that is still true.

MTPE of Poor Quality Source Texts: Some Practical Suggestions

2022-08-02T22:28:00.002-06:00

To achieve the best MT results, you should first correct the source text, when it is a scanned hard copy or an automatic transcription of recorded speech. Here are a few practical suggestions:

Choose the correct settings before running OCR. In particular, select the correct source language (you’ll see better suggestions during verification), select the correct graphic resolution for each page and the correct text direction for each piece of text, and de-skew and clean each page that requires it. Verification should be run by someone familiar with both the source language and the subject.
Correct misspelled or wrongly transcribed words.
Add “[sic]” after any word that you cannot identify and that you suspect is an artifact of the OCR process. This helps the post-editor focus on problem areas.
Capitalize proper nouns and acronyms.
Lower case incorrectly capitalized words.
Reassemble sentences broken up by periods (hard returns) or new lines (soft returns).
Feed the source text to the MT engine only after completing such corrections; doing otherwise will yield substandard results and will take longer to post-edit.

When the source text is good, you can skip pre-editing, but, when it is questionable or poor, pre-editing enhances the quality of the resulting machine translation and helps the post-editor achieve the desired quality.

An AutoHotkey solution to a memoQ problem

2021-07-27T07:00:00.001-06:00

The memoQ problem…

Some installations of memoQ suffer an annoying problem: cut and paste doesn’t work. The rest of the program works, as does copy and paste, but not the "paste" part of cut and paste: memoQ deletes your text at Ctrl+X all right, but it does not save it to the clipboard, so you have nothing to paste when you hit Ctrl+V.

If you try to perform the operation via the context menu, no luck, either: after Ctrl+X, paste (Ctrl+V) is greyed out.

Cut and Paste not working in memoQ

The problem appears unpredictably: you could have (as I do) two similar computers, with a similar panoply of software installed. On one cut and paste works as expected in memoQ, while in the other it doesn't.

memoQ’s support staff are aware of this problem, but (since they have never been able to reproduce it) their developers are unable to fix it. memoQ's support offer several suggestions that sometime work, from disabling other programs that might interfere with the clipboard, to deleting certain temporary files, and finally to that old favorite of all support organizations: reinstalling the program… but even reinstallation, for certain users, fails to correct the problem.

Fortunately, there is a simple workaround: instead of hitting Ctrl+X to cut and Ctrl+V to paste, you can add a step—copy (Ctrl+C), delete (Del), and finally paste (Ctrl+V)—but if you are accustomed to just using Ctrl+X/Ctrl+V in all other programs, you are likely to forget that you have to use different steps in memoQ.

...and the AutoHotkey solution

So we need a more permanent solution, and one is at hand (this also is thanks to a suggestion from memoQ support): using an AutoHotkey¹ script to replace the “cut” part of cut and paste.

Here is the script (complete with comments to explain what each step does):

#NoEnv  		; Recommended for performance and compatibility with future 
                        ; AutoHotkey releases.
SendMode Input  	; Recommended for new scripts due to its superior speed 
                        ; and reliability.
SetWorkingDir %A_ScriptDir%  ; Ensures a consistent starting directory.

^x:: 			; Assigns to the Ctrl+X shortcut the following actions:
#IfWinActive memoQ 	; ensures script works with memoQ only, not with other programs
Send ^c 		; Copy (as if "Ctrl+C" had been pressed)
Send {del} 		; Delete (as if the "Delete" key had been pressed)
#IfWinActive 		; end of the "works in memoQ only" part of the script
Return 			; end of the script

You can use this script "as is" if you already have AutoHotkey installed: just copy the above code to an empty text file and save it with an .ahk extension; then, whenever you need to work in memoQ, double click on the script file to launch it.

If you use other AutoHotkey scripts, you also can add the above code snippet to one of your other scripts (so long as none of them tries uses Ctrl+X as a hotkey). And you can even compile the script to an independent .exe file, to use on computers where AutoHotkey is not installed.

1 AutoHotkey is a free, open-source scripting language for Windows that allows users to easily create small to complex scripts.

Guest Post: Launching CLEAR Global: Translators without Borders Is 10 and Ready for More!

2021-07-26T07:00:00.001-06:00

by Jennifer Cajina-Grigsby

Translators without Borders begun when a small group of people translated information for aid organizations helping people hit by the Haiti earthquake 10 years ago. Driven to close the language gaps hindering critical humanitarian and international development efforts worldwide, the rapidly growing Translators without Borders team has achieved a lot since our founding. For example, we:

Translated information following the earthquake in Haiti, tsunamis in Indonesia, cyclones in Mozambique, and hurricanes in the USA.
Translated 1,900 Wikimedia medical articles in 83 languages, which helped over 40 million people access free and accurate health information.
Created multilingual chatbots to give people in the Democratic Republic of Congo and Nigeria accurate and reliable COVID-19 and Ebola information (read about Translators without Borders’ COVID-19 global response and glossary).
Started creating language maps in over 60 languages for organizations to better prepare for multilingual communication.

This would have been impossible without the support of donors, partners, and our community of linguists, translators, and local experts: over 60,000 volunteers contributing time and skills for a world without language barriers. Some have been with us for almost 10 years. Their experience working with Translators without Borders allows them to polish their translation skills, learn about the language technology we’re building, and get a solid foundation for their careers in translation.

Translators Without Borders recognizes the work of its volunteers by giving recommendations, references, and milestone certificates when the volunteers reach a certain word threshold. We foster a relationship with our community based on reciprocity, fairness, and shared values. Our community members work when they can, producing content for people who speak marginalized languages.

Thanks to this community, our impact has increased over the past years. Since our foundation, we have significantly grown as an organization, but much is yet to be done. Thus, with Translators without Borders at our core, we have evolved our brand to CLEAR Global, which includes CLEAR Insights and CLEAR Tech: entities working together for a more just society. Our goal is to make sure that the four billion people who speak a marginalized language are listened to, and can get the information they need, want, and understand. That’s what CLEAR is all about: Community, Language, Engagement, Accountability, and Reach.

ClearGlobal website

To go with this brand evolution, we’re running a campaign to lead us into the next 10 years. We want to raise funds for building diverse, scalable language technologies based on artificial intelligence and machine learning. Our teams and partners will use them to better communicate with local communities. We’ll implement solutions to help people who speak marginalized languages to ask for, receive, and share vital information.

As a nonprofit, we’re always seeking support. If our cause and growth resonates with you, you can join our community right now. If you want to do more to support our growth, you can also help us spread the word about our “10 years on. Ready for more” campaign or even make a donation. Every contribution counts and will contribute to improving other people’s lives.

About the author:

Jennifer Cajina-Grigsby, before joining Translators without Borders, worked as a freelance translator for US nonprofits. Jennifer has always been passionate about language diversity and how to help bridge the global language divide. Her desire to do more led her to Translators without Borders, a nonprofit helping people get vital information, and be heard, whatever language they speak.

Translations from Italian and into Italian

2021-07-13T09:56:00.006-06:00

A couple of links for those interested in Italian translation:

Nota del Traduttore, a YouTube series from Italian publisher Gruppo Mondadori, in which several Italian translators speak about their work.

Backstories: Afro-Italian Women Writers, in the July/August 2021 issue of WORDS without BORDERS, The Online Magazine for International Literature:

This issue presents writing by Afro-Italian women. In the face of xenophobic rhetoric and policies, Black Italians have pushed their country to confront its colonial past and engage with its present diversity.

Guest Post: The Studio Academy - Mastering File Types in Trados Studio

2021-07-05T13:15:00.003-06:00

by Michael Widemann

Even though I have been using Trados products for nearly 20 years now, I only started digging deeper with the release of Studio in 2009. And this for a good reason.

As a project manager responsible for delivering multilingual translation projects to my clients, I am confronted with ever more different file formats, many of which are specific to only one client. This is especially true for XML. But there is so much more: Different versions of Microsoft Office documents, FrameMaker, InDesign, csv and text files, JSON or YAML. Every file type is based on a completely different concept and each new version comes with new features that make established processes redundant.

What I needed was a completely different approach to how I use Studio. The defaults were not good enough anymore.

Then, in 2009, I also started working as a Trados trainer where I had the chance to work with freelance translators, project managers at agencies and localization specialist in small and large companies all over the world. And what I soon began to realize is that – even though everybody has their own workflows – most of them work with Studio’s default settings. They install it and go for it.

And it works. Even if you have never worked with such a tool, the fundamental concepts are easy to understand: translation memory, concordance, terminology integration. Saves time and money. Great. Plus 51 file types right out of the box. Studio handles them all.

After all, this is Studio’s concept: Whether you know how InDesign works, what an XML file is made up of or have mastered the intricacies of JSON files – Studio makes it possible for you translate them. No questions asked. No job you need to turn down because you do not have the required software. Studio – even in its standard installation – extracts the text it deems translation-worthy and presents it to you in a uniform working environment.

Yet there seems to be a problem...

All these options might be overwhelming. How can you possibly decide on whether to extract content from Master Pages in InDesign documents, decide on the right Parser settings or if it is necessary to insert a UTF-8-BOM, for example, when you have no idea what this is all about? And what's the deal with regular expressions and segmentation rules?

This is the problem I aim to solve with “The Studio Academy”: The complete guide to mastering file types in SDL Trados Studio:

- Detailed explanations on all available file type options, based on real-world examples.

- Everything you need to know about the concept behind file types in order to make the right decisions.

- Bonus information on embedded content, regular expressions, segmentation rules, XPath, ....

These modules are for you if...

- You don’t want a piece of software to make decisions for you. You want to be in control.

- You want to customize Studio to extract only the text you actually need. Not more, and certainly not less.

- You want to create your own file types to have the best solution for unknown file formats.

- You want to be able to handle files that do not follow any standard (e.g., HTML files copied to Excel) by using embedded content, regular expressions and customized segmentation rules like a pro.

Where and when to customize file type settings

About the author:

Michael Widemann is a project manager at a translation agency and an approved Trados trainer with 20 years’ experience in the industry. He also works as a translator and has published several books, mainly about music, some of them with Cosoc Grand Palace Publishing (his own publishing company). He is responsible for the German version of the Xbench manual, loves finding new ways to improve his workflow and hosts the podcast “Keine Zeit”, a weekly talk show about productivity, communication, motivation, goals, life and whatever else can go wrong.

Feed Burner Goes Away, and unfortunately so does your email subscription

2021-07-03T11:49:00.001-06:00

If you subscribed to receive updates from About Translation by email, please note that, since Google is going to remove or restrict Feedburner, your subscription will stop working in July 2021.

I've already removed the link on this page that allowed readers to subscribe, since there is little point in accepting new subscriptions, if the entire subscription service will stop working soon; I'm currently looking into alternatives to send the updates to this blog to the readers who still wish to receive them. In the meantime, please note that I also automatically announce new posts to this blog via my Twitter feed (@RSchiaffino).