Syntactically Guided Neural Machine Translation

Syntactically Guided Neural Machine Translation” by Felix Stahlberg, Eva Hasler, Aurelien Waite, and William Byrne. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), 2016, pp. 299-305.

Abstract

We investigate the use of hierarchical phrase-based SMT lattices in end-to-end neural machine translation (NMT). Weight pushing transforms the Hiero scores for complete translation hypotheses, with the full translation grammar score and full ngram language model score, into posteriors compatible with NMT predictive probabilities. With a slightly modified NMT beam-search decoder we find gains over both Hiero and NMT decoding alone, with practical advantages in extending NMT to very large input and output vocabularies.

BibTeX entry:

@inproceedings{P16-2049,
   author = {Felix Stahlberg and Eva Hasler and Aurelien Waite and William
	Byrne},
   title = {Syntactically Guided Neural Machine Translation},
   booktitle = {Proceedings of the 54th Annual Meeting of the Association
	for Computational Linguistics (Volume 2: Short Papers)},
   pages = {299--305},
   publisher = {Association for Computational Linguistics},
   year = {2016},
   url = {http://aclweb.org/anthology/P16-2049}
}

Back to Bill Byrne publications.