My amateur method for translations

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]