Fair is Better than Sensational:Man is to Doctor as Woman is to Doctor · HackerPapers discussions

Fair is Better than Sensational:Man is to Doctor as Woman is to Doctor — HN submission

Tue, 20 Jan 2026 12:04:01 GMT

Fair is Better than Sensational:Man is to Doctor as Woman is to Doctor (2019)

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Fair is Better than Sensational:Man is to Doctor as Woman is to Doctor — mentioned by spindump8930

Wed, 14 May 2025 20:49:39 GMT

First off, this interface is very nice and a pleasure to use, congrats! Are you using word2vec for these, or embeddings from another model? I also wanted to add some flavor since it looks like many folks in this thread haven't seen something like this - it's been known since 2013 that we can do this (but it's great to remind folks especially with all the "modern" interest in NLP). It's also known (in some circles!) that a lot of these vector arithmetic things need some tricks to really shine. For example, excluding the words already present in the query[1]. Others in this thread seem…

Paper and discussion history. A mention is not an endorsement.

Fair is Better than Sensational:Man is to Doctor as Woman is to Doctor — mentioned by gdy

Tue, 16 Jul 2019 18:37:37 GMT

You missed the word 'exactly'. Can you summarize her work so that it doesn't sound trivial or bogus? Just looking at the titles I expect something similar in quality to articles debunked here: https://arxiv.org/abs/1905.09866

Paper and discussion history. A mention is not an endorsement.

Fair is Better than Sensational:Man is to Doctor as Woman is to Doctor — mentioned by JD557

Tue, 16 Jul 2019 09:06:16 GMT

At first I thought "What's the big deal? You also remove the query from recommender systems, for example. It's an obvious uninteresting result!". But then I read the linked article [Nissim 2019] and it all became much clearer with te example in the title: "Man is to Doctor as Woman is to Doctor". If you remove "Doctor" from the results, you'll get "Nurse" instead, not because the dataset/society/... is biased, but because you inserted the bias in your model! With this small "optimization" (and others presented in the article, such as the "threshold-method" and hand-picked results from the…

Paper and discussion history. A mention is not an endorsement.

Fair is Better than Sensational:Man is to Doctor as Woman is to Doctor — mentioned by markchen90

Sun, 07 Jul 2019 08:14:35 GMT

These analogies need to be taken with a grain of salt. For instance, king - man + woman actually returns king (since woman - man ~= 0). It's only queen when you ban the words king, man, or woman (since the embeddings of queen and king are close). See Ian's tweet https://twitter.com/goodfellow_ian/status/113352818965167718... or the linked paper https://arxiv.org/pdf/1905.09866.pdf for more information.

Paper and discussion history. A mention is not an endorsement.

Fair is Better than Sensational:Man is to Doctor as Woman is to Doctor — HN submission

Wed, 29 May 2019 17:55:35 GMT

Fair Is Better Than Sensational:Man Is to Doctor as Woman Is to Doctor

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Fair is Better than Sensational:Man is to Doctor as Woman is to Doctor — HN submission

Wed, 29 May 2019 00:22:02 GMT

Fair Is Better Than Sensational: Man Is to Doctor as Woman Is to Doctor [pdf]

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.