DFKI-LT - Learning Bilingual Projections of Embeddings for Vocabulary Expansion in Machine Translation

Pranava Swaroop Madhyastha, Cristina Espaņa i Bonet
Learning Bilingual Projections of Embeddings for Vocabulary Expansion in Machine Translation
1 Proceedings of the 2nd Workshop on Representation Learning for NLP, Pages 139-145, Vancouver, BC, Canada, Association for Computational Linguistics, Association for Computational Linguistics, 8/2017
 
We propose a simple log-bilinear softmax-based model to deal with vocabulary expansion in machine translation. Our model uses word embeddings trained on significantly large unlabelled monolingual corpora and learns over a fairly small, word-to-word bilingual dictionary. Given an out-of-vocabulary source word, the model generates a probabilistic list of possible translations in the target language using the trained bilingual embeddings. We integrate these translation options into a standard phrase-based statistical machine translation system and obtain consistent improvements in translation quality on the English–Spanish language pair. When tested over an out-of-domain test-set, we get a significant improvement of 3.9 BLEU points
 
Files: BibTeX, W17-2617, document.pdf