BROADCASTS.com

The topic of bias in word embeddings gets yet another pass this week. It all started a few years ago, when an analogy task performed on Word2Vec embeddings showed some indications of gender bias around professions (as well as other forms of social bias getting reproduced in the algorithm\u2019s embeddings). We covered the topic again a while later, covering methods for de-biasing embeddings to counteract this effect. And now we\u2019re back, with a second pass on the original Word2Vec analogy task, but where the researchers deconstructed the \u201crules\u201d of the analogies themselves and came to an interesting discovery: the bias seems to be, at least in part, an artifact of the analogy construction method. Intrigued? So were we\u2026\n\nRelevant link:\nhttps://arxiv.org/abs/1905.09866