News for hackers. Stuff that matters.

A comment on Multilingual word vectors in 78 languages.

Re:Multilingual word vectors in 78 languages by nicodemus26 on Friday April 21, 2017 @04:44PM (#14169299)
The next trick would be to create a matrix that is the closest to all of the languages and doesn't have gaps from missing words. Using English as the identity is probably a bit ethnocentric -- another reification of the three-percent problem of literary translation: http://www.rochester.edu/College/translation/threepercent/ .

Maybe we can call this new matrix Mondoshawan?

[ Parent | on HN ]
Re:Multilingual word vectors in 78 languages by sls56 on Saturday April 22, 2017 @02:15PM (#14173837)
Yes definitely! We didn't want to complicate the repository, but from a few in-house experiments we already know that it is possible to improve the rotation matrices by: 1. First aligning to a reference language (English) 2. Then defining a new reference as the mean vector of all the languages for each entry in the training dictionary 3. Re-align the languages to this new reference "language" 4. Iteratively repeat 2 and 3 to convergence

As you suggest potentially this mean language is itself really high quality word vectors; but we haven't looked at this yet...

[ Parent | on HN ]