Word Translation Without Parallel Data · HackerPapers discussions

Word Translation Without Parallel Data — mentioned by yorwba

Wed, 23 Jan 2019 22:05:01 GMT

I think meaning isn't really separable from structure. But assuming you're talking about semantics vs. syntax, then continuous representations can certainly do a lot more than just syntax. They can model how words change in meaning over time [1], they can identify words that mean the same in different languages [2] and use that to translate whole sentences [3] without ever seeing a direct translation. Of course none of those tasks are solved to perfection yet, but some kind of meaning is definitely being captured. [1] https://arxiv.org/abs/1703.00607 [2] https://arxiv.org/abs/1710.04087 [3]…

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

Word Translation Without Parallel Data — mentioned by heydenberk

Fri, 31 Aug 2018 19:08:26 GMT

The previous paper they mention explains the core insight that makes unsupervised translation possible: https://arxiv.org/abs/1710.04087 The original paper didn't receive the attention I thought it would, but I continue to think this is a fascinating result which has deep implications for machine learning and for linguistics.

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

Word Translation Without Parallel Data — mentioned by yorwba

Thu, 22 Mar 2018 10:35:24 GMT

The Gaussian mixture representation is quite interesting, so thanks for the link. But it seems like they do not make use of the relative position of words in the text either. They simply maximize the margin of the expected likelihood for words that occur in the same context over those that do not. However, in most cases it's probably actually better to ignore word order, since that captures more semantic relatedness rather than the syntactic features that influence word order. It also lets you translate between languages that do not necessarily have similar grammar: "Word Translation Without…

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

Word Translation Without Parallel Data — HN submission

Mon, 19 Mar 2018 21:37:09 GMT

Word Translation Without Parallel Data

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