Parsers as language models for statistical machine translation

Matt Post, Daniel Gildea


Abstract
Most work in syntax-based machine translation has been in translation modeling, but there are many reasons why we may instead want to focus on the language model. We experiment with parsers as language models for machine translation in a simple translation model. This approach demands much more of the language models, allowing us to isolate their strengths and weaknesses. We find that unmodified parsers do not improve BLEU scores over ngram language models, and provide an analysis of their strengths and weaknesses.
Anthology ID:
2008.amta-papers.16
Volume:
Proceedings of the 8th Conference of the Association for Machine Translation in the Americas: Research Papers
Month:
October 21-25
Year:
2008
Address:
Waikiki, USA
Venue:
AMTA
SIG:
Publisher:
Association for Machine Translation in the Americas
Note:
Pages:
172–181
Language:
URL:
https://aclanthology.org/2008.amta-papers.16
DOI:
Bibkey:
Cite (ACL):
Matt Post and Daniel Gildea. 2008. Parsers as language models for statistical machine translation. In Proceedings of the 8th Conference of the Association for Machine Translation in the Americas: Research Papers, pages 172–181, Waikiki, USA. Association for Machine Translation in the Americas.
Cite (Informal):
Parsers as language models for statistical machine translation (Post & Gildea, AMTA 2008)
Copy Citation:
PDF:
https://preview.aclanthology.org/remove-xml-comments/2008.amta-papers.16.pdf