Wouldn’t it be nice if machine translation asked how you want to translate ‘you’?
Let’s do a little experiment: go to your favourite machine translation website, such as Google Translate, and ask it to translate a sentence from English into German which has the pronoun you in it. Will it be translated as the informal casual du, or as the formal polite Sie? It’s anyone’s guess really, most machine translators seem to choose one or the other pretty much arbitrarily.
In case you didn’t know, German is one of those languages where you have two ways or “levels” of talking to people. People you are close to, such as friends and family, you address them with the informal pronoun du. People you are more distant with, strangers you’ve just met and so on, you address them with the formal pronoun Sie. English has only one word for both levels, the pronoun you, so this distinction doesn’t really exist in English. But in most European languages it does, including German.
Back to machine translation. Wouldn’t it be nice if your machine translator simply asked you which level of formality you wanted, instead of guessing? Because guessing is what the machines do, mostly. Machines are good at computing likelihoods and probabilities, so they are able to guess which level of formality is more “normal” or “usual” for any sentence, based on the data they have been trained on. The only problem is, this might be the complete opposite of what you have in mind at this very moment. Suppose you’re translating something ordinary, such as please sit down or are you hungry? How is a machine supposed to guess correctly who you’re saying it to? To your grandson? To your mother-in-law? Or to a customer in your restaurant? Which level of formality is required? No artificial intelligence can ever guess what only you can know. (By the way, it’s du for the grandson and Sie for the customer, the mother-in-law is a borderline case.)
Fairslator is a machine translator that doesn’t try to guess such things. Fairslator asks you instead. In Fairslator, if you tell it to translate something with you in it, you will be offered a list of options where you can select what exactly you mean by that you: which level of formality, and also whether it’s supposed to be a singular you (when you’re talking to one person) or a plural you (when you’re talking to several people).
Can your usual machine translator do that? Probably not. As far as we know, Fairslator is the first and only translation service in the world that doesn’t just spit out one single translation, but asks you what you mean by that. Try it for yourself and tell all your German-speaking friends – but don’t forget to use the correct version of you!
October 2024 —
We were talking about bias in machine translation
at a Translating Europe Workshop organised by the European Commission in Prague
as part of Jeronýmovy dny,
a series of public lectures and seminars on translation and interpreting.
Video here »
December 2023 —
Fairslator presented a workshop on bias in machine translation
at the European Commission's
Directorate-General for Translation,
attended by translation-related staff from all EU institutions.
November 2023 —
Fairslator went to Translating and the Computer,
an annual conference on translation technology in Luxembourg,
to present its brand new API.
Proceedings from this conference are here, our paper starts on page 98.
November 2023 —
We were talking about gender bias, gender rewriting and Fairslator
at the EAFT Summit
in Barcelona where we also launched an exciting spin-off
project there:
Genderbase,
a multilingual database of gender-sensitive terminology.
February 2023 —
We spoke to machinetranslation.com
about bias in machine translation, about Fairslator, and about our vision for “human-assisted machine translation”.
Read the interview here:
Creating an Inclusive AI Future: The Importance of Non-Binary Representation »
October 2022 —
We presented Fairslator at the
Translating and the Computer
(TC44) conference, Europe's main annual event for computer-aided translation, in Luxembourg.
Proceedings from this conference are here,
the paper that describes Fairslator starts on page 90.
Read our impressions from TC44 in this thread on
Twitter
and
Mastodon.
September 2022 —
In her article
Error sources in machine translation: How the algorithm reproduces unwanted gender roles
(German: Fehlerquellen der maschinellen Übersetzung: Wie der Algorithmus ungewollte Rollenbilder reproduziert),
Jasmin Nesbigall of oneword GmbH talks about bias in machine translation
and recommends Fairslator as a step towards more gender fairness.
September 2022 —
Fairslator was presented at the
Text, Speech and Dialogue
(TSD) conference in Brno.
August 2022 —
Translations in London are talking about Fairslator in their blog post
Overcoming gender bias in MT.
They think the technology behind Fairslator could be useful in the translation industry
for faster post-editing of machine-translated texts.
July 2022 —
We presented a paper titled A Taxonomy of Bias-Causing Ambiguities in Machine Translation
at a Workshop on Gender Bias in Natural Language Processing
during the 2022 Annual Conference of the North American Chapter of the Association for Computational Linguistics
in Seattle.
May 2022 —
Slator.com, a website for the translation industry, asked us for a guest post and of course we didn't say no.
Read What You Need to Know About Bias in Machine Translation »