Abstract
This paper describes a method that successfully exploits simple syntactic features for n-best translation candidate reranking using perceptrons. Our approach uses discriminative language modelling to rerank the n-best translations generated by a statistical machine translation system. The performance is evaluated for Arabic-to-English translation using NIST’s MT-Eval benchmarks. Whilst parse trees do not consistently help, we show how features extracted from a simple Part-of-Speech annotation layer outperform two competitive baselines, leading to significant BLEU improvements on three different test sets.- Anthology ID:
- 2010.amta-papers.1
- Volume:
- Proceedings of the 9th Conference of the Association for Machine Translation in the Americas: Research Papers
- Month:
- October 31-November 4
- Year:
- 2010
- Address:
- Denver, Colorado, USA
- Venue:
- AMTA
- SIG:
- Publisher:
- Association for Machine Translation in the Americas
- Note:
- Pages:
- Language:
- URL:
- https://aclanthology.org/2010.amta-papers.1
- DOI:
- Cite (ACL):
- Simon Carter and Christof Monz. 2010. Discriminative Syntactic Reranking for Statistical Machine Translation. In Proceedings of the 9th Conference of the Association for Machine Translation in the Americas: Research Papers, Denver, Colorado, USA. Association for Machine Translation in the Americas.
- Cite (Informal):
- Discriminative Syntactic Reranking for Statistical Machine Translation (Carter & Monz, AMTA 2010)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/2010.amta-papers.1.pdf