Learning unsupervised word translations without adversaries
T Mukherjee, M Yamada… - Proceedings of the 2018 …, 2018 - aclanthology.org
Word translation, or bilingual dictionary induction, is an important capability that impacts
many multilingual language processing tasks. Recent research has shown that word
translation can be achieved in an unsupervised manner, without parallel seed dictionaries
or aligned corpora. However, state of the art methods unsupervised bilingual dictionary
induction are based on generative adversarial models, and as such suffer from their well
known problems of instability and hyper-parameter sensitivity. We present a statistical …
many multilingual language processing tasks. Recent research has shown that word
translation can be achieved in an unsupervised manner, without parallel seed dictionaries
or aligned corpora. However, state of the art methods unsupervised bilingual dictionary
induction are based on generative adversarial models, and as such suffer from their well
known problems of instability and hyper-parameter sensitivity. We present a statistical …
Learning Unsupervised Word Translations Without Adversaries
TM Hospedales, M Yamada, T Mukherjee - Proceedings of the 2018 …, 2018 - cir.nii.ac.jp
Word translation, or bilingual dictionary induction, is an important capability that impacts
many multilingual language processing tasks. Recent research has shown that word
translation can be achieved in an unsupervised manner, without parallel seed dictionaries
or aligned corpora. However, state of the art methods unsupervised bilingual dictionary
induction are based on generative adversarial models, and as such suffer from their well
known problems of instability and hyper-parameter sensitivity. We present a statistical …
many multilingual language processing tasks. Recent research has shown that word
translation can be achieved in an unsupervised manner, without parallel seed dictionaries
or aligned corpora. However, state of the art methods unsupervised bilingual dictionary
induction are based on generative adversarial models, and as such suffer from their well
known problems of instability and hyper-parameter sensitivity. We present a statistical …
Showing the best results for this search. See all results