Using an online tool and having a well-defined process can save a lot of time

I have noticed that some people, even if they are not fluent in English, rarely use any tool to translate texts from English to their first language; and the same can happen to English-speakers who are trying to write or translate something into another language. Even for people who are fluent in a second language, a translation tool can save time and help in choosing vocabulary and sentence forms. Sure, everyone use Google Translate; but it only supports 5k characters at a time (unlike the now defunct Translator's Toolkit - RIP, my friend). Therefore, I decided to describe the simple procedure I usually adopt to translate a text from Portuguese to English (or vice-versa), using DeepL. I would appreciate suggestions and/or alerts about alternative procedures or tools.

I have previously used this method to write this post for the EA Forum - which is a translation of a text previously published in our Medium Altruísmo Eficaz Brasil. It helped translate some 80,000 hours content, and it's been a lot of help for translating some SEP entries. Also, this very same text started as a translation of a personal Medium post, which I wrote to share these tips with Brazilian colleagues.

Of course, this does not apply to professional translators, nor if none of the languages are English, which is the standard language of NLP algorithms; when I translate an expression from Portuguese into French, for example, it is obvious that the algorithm uses English as an "intermediary".

1. Convert the text to .docx: DeepL only accepts Microsoft Word documents. This means that to translate a web page or a .pdf file, you must first convert it to .docx. There are several tools for this - the one I usually use is pdf2doc.

2. Using DeepL: it's simple - I upload, select the output language, and after a few minutes, it delivers a .docx with the translated text.

Problems: tables, graphs and images tend to change their formatting and compromise the result. It may be better to preemptively remove them from the document and only use the text itself as input.

3. Convert the resulting file to another format: the free version of DeepL returns a .docx that is protected against editing. That means you can't proofread the text. This can be solved by converting it to another format. In my case, I usually convert the translation to .pdf and then to .docx again. But you can bypass this obstacle by opening it on Google Docs, too.

4. Revise the text: there will still be some errors in the final text. But for someone with sufficient command of both languages and the subject matter, they will be relatively easy to spot and correct (Linguee has been my favorite tool for short expressions). Of course, don’t be afraid of asking for help, too.

(when in doubt, I convert the translation back to the first language and see if it still makes sense)

Situations where someone would probably benefit from this process:

a) students reading a text on a known subject but in a foreign language: they are often fluent enough to notice when a construction is semantically inconsistent (i.e., intermediate level of reading skills), but their knowledge of the vocabulary may still be insufficient - i.e., translating the text beforehand avoids having to use a bilingual dictionary.

b) translating relatively short texts (less than 50 pages - e.g., posts, papers, or presentations…)

c) people writing a text (e.g. a post or a paper) in a foreign language they have mastered (i.e., B2 or even C1 of the European framework), but who still find the vocabulary or grammatical constructions laborious - i.e., it is often faster to write in your mother tongue and then translate than to write directly in the final language.

I think this procedure might be particularly useful for non-anglophone EAs who want to try their hand at publishing in this Forum - maybe inspired by Aaron Gertler's talk in the EAGx.

People who would not benefit from this procedure:

a) Professional translators – especially with literary texts.

b) Translations that do not involve English – as I said before, this is the standard language of NLP algorithms.

c) People without any skill in the second language: the result is likely to end up full of mistakes. This process is supposed to save you time, but not (yet) to replace your language skills. If you can’t read in this language, you should ask for help, instead.

People actively trying to practice a language that they are learning: this method can be useful to check your accuracy after writing a text by translating it back to your native language, but you’re likely to learn more by writing the text in the second language first.

[Thanks to Gavin Taylor for a deep and helpful revision of this text, and to Aaron Gertler on suggestions for improving it]

15

0
0

Reactions

0
0

More posts like this

Comments2


Sorted by Click to highlight new comments since:

Thanks for posting this resource! Questions:

  • Do you find DeepL to be better than Google Translate and other options overall? Just for English/Portuguese translation?
  • Would you be open to adding a bit of material about how your group has used translation and/or how you think it might be useful to other people doing EA work? Right now, this post just reads like a handy guide to a skill; before I move it out of the "personal blog" category, I'd want to see some note on its relevance to EA.

Thanks!

I find DeepL more useful because, unlike Google Translate, I don't have to slice my text into 5k characters bits (though I often appeal to Google and Linguee when I want to check small excerpts). It has provided me with a better experience than Microsoft Word translation tool, too.

Sure, I added some remarks on how we used it to translate some EA-related material. But, honestly, it's basically a handy guide.

More from Ramiro
Curated and popular this week
Sam Anschell
 ·  · 6m read
 · 
*Disclaimer* I am writing this post in a personal capacity; the opinions I express are my own and do not represent my employer. I think that more people and orgs (especially nonprofits) should consider negotiating the cost of sizable expenses. In my experience, there is usually nothing to lose by respectfully asking to pay less, and doing so can sometimes save thousands or tens of thousands of dollars per hour. This is because negotiating doesn’t take very much time[1], savings can persist across multiple years, and counterparties can be surprisingly generous with discounts. Here are a few examples of expenses that may be negotiable: For organizations * Software or news subscriptions * Of 35 corporate software and news providers I’ve negotiated with, 30 have been willing to provide discounts. These discounts range from 10% to 80%, with an average of around 40%. * Leases * A friend was able to negotiate a 22% reduction in the price per square foot on a corporate lease and secured a couple months of free rent. This led to >$480,000 in savings for their nonprofit. Other negotiable parameters include: * Square footage counted towards rent costs * Lease length * A tenant improvement allowance * Certain physical goods (e.g., smart TVs) * Buying in bulk can be a great lever for negotiating smaller items like covid tests, and can reduce costs by 50% or more. * Event/retreat venues (both venue price and smaller items like food and AV) * Hotel blocks * A quick email with the rates of comparable but more affordable hotel blocks can often save ~10%. * Professional service contracts with large for-profit firms (e.g., IT contracts, office internet coverage) * Insurance premiums (though I am less confident that this is negotiable) For many products and services, a nonprofit can qualify for a discount simply by providing their IRS determination letter or getting verified on platforms like TechSoup. In my experience, most vendors and companies
 ·  · 4m read
 · 
Forethought[1] is a new AI macrostrategy research group cofounded by Max Dalton, Will MacAskill, Tom Davidson, and Amrit Sidhu-Brar. We are trying to figure out how to navigate the (potentially rapid) transition to a world with superintelligent AI systems. We aim to tackle the most important questions we can find, unrestricted by the current Overton window. More details on our website. Why we exist We think that AGI might come soon (say, modal timelines to mostly-automated AI R&D in the next 2-8 years), and might significantly accelerate technological progress, leading to many different challenges. We don’t yet have a good understanding of what this change might look like or how to navigate it. Society is not prepared. Moreover, we want the world to not just avoid catastrophe: we want to reach a really great future. We think about what this might be like (incorporating moral uncertainty), and what we can do, now, to build towards a good future. Like all projects, this started out with a plethora of Google docs. We ran a series of seminars to explore the ideas further, and that cascaded into an organization. This area of work feels to us like the early days of EA: we’re exploring unusual, neglected ideas, and finding research progress surprisingly tractable. And while we start out with (literally) galaxy-brained schemes, they often ground out into fairly specific and concrete ideas about what should happen next. Of course, we’re bringing principles like scope sensitivity, impartiality, etc to our thinking, and we think that these issues urgently need more morally dedicated and thoughtful people working on them. Research Research agendas We are currently pursuing the following perspectives: * Preparing for the intelligence explosion: If AI drives explosive growth there will be an enormous number of challenges we have to face. In addition to misalignment risk and biorisk, this potentially includes: how to govern the development of new weapons of mass destr
jackva
 ·  · 3m read
 · 
 [Edits on March 10th for clarity, two sub-sections added] Watching what is happening in the world -- with lots of renegotiation of institutional norms within Western democracies and a parallel fracturing of the post-WW2 institutional order -- I do think we, as a community, should more seriously question our priors on the relative value of surgical/targeted and broad system-level interventions. Speaking somewhat roughly, with EA as a movement coming of age in an era where democratic institutions and the rule-based international order were not fundamentally questioned, it seems easy to underestimate how much the world is currently changing and how much riskier a world of stronger institutional and democratic backsliding and weakened international norms might be. Of course, working on these issues might be intractable and possibly there's nothing highly effective for EAs to do on the margin given much attention to these issues from society at large. So, I am not here to confidently state we should be working on these issues more. But I do think in a situation of more downside risk with regards to broad system-level changes and significantly more fluidity, it seems at least worth rigorously asking whether we should shift more attention to work that is less surgical (working on specific risks) and more systemic (working on institutional quality, indirect risk factors, etc.). While there have been many posts along those lines over the past months and there are of course some EA organizations working on these issues, it stil appears like a niche focus in the community and none of the major EA and EA-adjacent orgs (including the one I work for, though I am writing this in a personal capacity) seem to have taken it up as a serious focus and I worry it might be due to baked-in assumptions about the relative value of such work that are outdated in a time where the importance of systemic work has changed in the face of greater threat and fluidity. When the world seems to