It asks you how you want to translate ‘you’.
In case you didn't know, Irish is one of the many language that have two words for you, one when you're talking to one person (tú) and another when you're talking to two or more people (sibh). In fact, most European languages are like that, it's English that's being the odd one out for having only one word for both.
Now 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 Irish which has you in it, such as where are you. Will it be translated with the singular tú, or with the plural sibh?
Most translation apps tend to go for the singular version of you most of the time. But suppose you wanted to say the sentence to a group of people. Well, if you do actually speak Irish, then it will be easy for you to know which word or words in the translation you're supposed to change. But what if you don't speak the language, or don't speak it well enough to be sure? Wouldn't it be better if the app simply asked you which meaning of you you want?
Unfortunately, machine translators don't have the ability to ask questions. Whenever they find themselves in a situation of ambiguity – like now when they don't know whether you refers to one person or many – they simply pick whichever option seems more likely, based on whichever occured frequently in their training data. In other words, the machine will make an assumption. This assumption may well be correct for most people most of the time, but it may not be correct for you at this particular moment when you are about to speak to a group of people and not just one person.
Enter Fairslator. Fairslator is different a translation tool because it doesn't make any assumptions and because it does ask questions. If you ask Fairslator for the Irish translation of a sentence with you in it, and if it isn't clear from the rest of the sentence whether you mean one person or many, the app will give you a choice. Only then, depending on what you have answered, will it give you the appropriate translation. The translation you get will be based on what you mean, not on what the machine assumes you mean.
Fairslator is pretty much the first translation app in the world that has this ability: the ability to ask follow-up questions if it has encountered an ambiguity in the source text. OK, maybe not completely first, because Google has been experimenting with something similar for gender-specific translations in some language pairs, and DeepL sometimes gives you a choice between formal and informal forms of address in languages that have them. But Fairslator outperforms them both because it detects a wider range of ambiguities – and is certainly the only one that can do it for Irish.
To summarize, Fairslator is a new kind of translation service: one that doesn’t just spit out one single translation but asks you what you mean. Try it for yourself and tell all your Irish-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 »