Hacker News Reader

Comment by protomyth | Hacker News Reader

Did you research focus on English or does the nearly the same biases hold for all modern languages? I would love to see a competently trained person try this with the Asian and Native American languages.

I dearly hope we will let the bias "humanity is good, don't kill us" stay in.

View on HN

That's definitely one of our main areas for future research. So far, the only part of the paper where we consider other languages is in studying how model bias affects language translation:

Unsurprisingly, today’s statistical machine translation systems reflect existing gender stereotypes. Translations to English from many gender-neutral languages such as Finnish, Estonian, Hungarian, Persian, and Turkish lead to gender-stereotyped sentences. For example, Google Translate converts these Turkish sentences with genderless pronouns: "O bir doktor. O bir hems¸ire." to these English sentences: "He is a doctor. She is a nurse." A test of the 50 occupation words used in the results presented in Figure 1 shows that the pronoun is translated to “he” in the majority of cases and "she" in about a quarter of cases; tellingly, we found that the gender association of the word vectors almost perfectly predicts which pronoun will appear in the translation.

See section on "Effects of bias in NLP applications" http://randomwalker.info/publications/language-bias.pdf

My German professor mentioned a few times in class about how automated translators had picked up sexist biases because of older training materials.

Which is to me rather a sign of how society changes meaning of the language to indoctrinate a kind of social propaganda. Greetings from George Orwell's 1984.

In fairness, there's a distinction to be made here between directed and undirected change.

When SJW warrior groups make campaigns that from now on some list of words has to be considered as racist, sexist, ...ist etc. I think one can talk of directed change.

..what if those words are?

At least people before did not consider them to be. This shows that proving that say are is not so easy.

Or people before didn't care if they are?

It's also a sign of how blind adherence to tradition causes old biases to persist and prevents any kind of progress, good or bad.

Reply on news.ycombinator.com