Exploiting Similarities among Languages for Machine Translation · HackerPapers discussions

Exploiting Similarities among Languages for Machine Translation — mentioned by exgrv

Thu, 02 Mar 2017 14:59:05 GMT

Models are trained independently for each language. So unfortunately, you cannot directly compare words from different languages using these vectors. If you have a bilingual dictionary, you might try to learn a linear mapping from one language to the other (e.g. see https://arxiv.org/abs/1309.4168 for this approach).

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

Exploiting Similarities among Languages for Machine Translation — HN submission

Sat, 22 Aug 2015 09:42:49 GMT

Exploiting Similarities Among Languages for Machine Translation (2013)

6 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

Exploiting Similarities among Languages for Machine Translation — mentioned by Smerity

Sun, 14 Jun 2015 20:41:42 GMT

I'm uncertain whether you mean the algorithm or the output. The question is interesting to both however. The most common method for producing word vectors, skip-grams with negative sampling, has been shown to be equivalent to implicitly factorizing a word-context matrix[1]. A related algorithm, GloVe, only uses a word-word co-occurrence matrix to achieve a similar result[2]. You can also view the output as an embedding in a high dimensional space (hence the name word vectors) but more surprisingly you can learn a linear mapping between vector spaces of two languages, which lends it…

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

Exploiting Similarities among Languages for Machine Translation — mentioned by eadlam

Fri, 04 Oct 2013 12:30:23 GMT

Stanford Ph.D. student Richard Socher appreciates the work Google and others are doing to build neural networks that can understand human language. He just thinks his work is more useful ... "We’re actually able to put whole sentences and longer phrases into vector spaces without ignoring the order of the words." Wait, didn't Mikolov et al. (Google) [just figure out][1] how to put entire languages into vector spaces? [1]: http://arxiv.org/abs/1309.4168

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