Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings · HackerPapers discussions

Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings — mentioned by thu2111

Fri, 18 Sep 2020 08:46:43 GMT

Evidence suggests the opposite: they would write a self-congratulatory blog post about it. For example the work Google does on "de-biasing AI" is all about taking ML models and warping its understanding of the world to reflect ideological priorities. https://arxiv.org/abs/1607.06520

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

Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings — mentioned by tastroder

Tue, 24 Sep 2019 05:21:45 GMT

Yeah, besides the fact that this compositionality is relatively unique to word2vec, research on the biases pre-trained models express is pretty available. Linked a few below for those interested. Most of the issues are down to the same phenomenon discussed here in the context of ImageNet, the input texts were biased and the algorithm learned said bias. [0] https://arxiv.org/abs/1607.06520 "Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings " [1] http://proceedings.mlr.press/v97/brunet19a/brunet19a.pdf "Understanding the Origins of Bias in Word Embeddings" [2]…

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

Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings — mentioned by yorwba

Tue, 16 Jul 2019 10:36:48 GMT

> The authors justed picked the 10th example in the list without clearly stating it. That's not an accurate description what Bolukbasi et al (2016) [0] did. In particular, they do not list x close to lovely + he - she and then pick arbitrarily from that list. Instead, they explicitly reject that approach (see appendix A), because they're looking for pairs of words that are maximally gendered. They do that by finding x and y such that the angle between x - y and she - he is minimized. Since the task they're solving is different, you can't fault them for getting different results. [0]…

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

Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings — mentioned by kvb

Wed, 31 Oct 2018 18:53:26 GMT

word2vec[0]: computer programmer - man + woman --------------------- = homemaker Basilica? [0] - https://arxiv.org/pdf/1607.06520.pdf

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

Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings — mentioned by ASpring

Wed, 31 Oct 2018 18:11:51 GMT

How do you plan to counter the harmful societal biases that embeddings embody? See Bolukbasi (https://arxiv.org/pdf/1607.06520.pdf) and Caliskan (http://science.sciencemag.org/content/356/6334/183) While these examples are solely language based, it is easy to imagine the transfer to other domains.

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

Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings — mentioned by rspeer

Tue, 20 Mar 2018 07:52:13 GMT

It's interesting and slightly uncomfortable that the illustration for similar words uses the word "man" as an example, given the gender biases that result from learning word vectors solely from word distributions. To explain, although I’m sure the author himself is familiar with the issue: For any word that is disproportionately associated with one gender in the corpus, the model will learn that gender difference as part of the representation of the word, pretty much baking it into all applications. [1] It's all fun and games when this helps you find the difference between "king" and "queen"…

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

Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings — mentioned by rspeer

Thu, 12 Oct 2017 04:36:48 GMT

I consider it very important to fight bias in AI, but I fundamentally do not understand this article's take. The thing stopping AI researchers from obtaining unbiased training data is not that we're waiting for laywers to give us permission. The thing stopping us is that the right training data is already hard to find, and unbiased training data is the hardest of all to find because it doesn't exist. Google, for example, does not need permission. They can acquire and train on basically any data they want if they put their mind to it. And Google is completely shit at deploying unbiased AI.…

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

Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings — mentioned by rspeer

Mon, 10 Jul 2017 15:40:11 GMT

I think the OP might have been looking for code that already exists, not just techniques for how to build it. But I have some opinions on these techniques. LDA is not very controllable. It gives you a set number of clusters. Run it again and you get different clusters. It can't give you documents that are similar to a particular document that you asked for, except to say that all the documents that happen to be in a cluster at the time are similar. There are indeed up-to-date things you can do with word vectors -- though I'm sad that the tutorials always point to word2vec or GloVe, as if it's…

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

Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings — HN submission

Mon, 09 Jan 2017 18:03:23 GMT

Man to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings

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

Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings — mentioned by gugagore

Sat, 24 Sep 2016 20:29:15 GMT

Yes! Here's an example: http://arxiv.org/abs/1607.06520

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

Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings — mentioned by gugagore

Sat, 24 Sep 2016 20:28:50 GMT

You are only talking about supervised learning. And the bias people are probably talking about is bias in the data, not bias in the "input", as you put it. See http://arxiv.org/abs/1607.06520 for a counterexample to your point.

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

Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings — HN submission

Wed, 27 Jul 2016 18:53:24 GMT

Man Is to Computer Programmer as Woman Is to Homemaker? Debiasing Word Embedding

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

Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings — HN submission

Mon, 25 Jul 2016 13:33:02 GMT

Debiasing Word Embeddings

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