Non-linear n-best List Reranking with Few Features

Artem Sokolov, Guillaume Wisniewski, François Yvon


Abstract
In Machine Translation, it is customary to compute the model score of a predicted hypothesis as a linear combination of multiple features, where each feature assesses a particular facet of the hypothesis. The choice of a linear combination is usually justified by the possibility of efficient inference (decoding); yet, the appropriateness of this simple combination scheme to the task at hand is rarely questioned. In this paper, we propose an approach that replaces the linear scoring function with a non-linear scoring function. To investigate the applicability of this approach, we rescore n-best lists generated with a conventional machine translation engine (using a linear scoring function for generating its hypotheses) with a non-linear scoring function learned using the learning-to-rank framework. Moderate, though consistent, gains in BLEU are demonstrated on the WMT’10, WMT’11 and WMT’12 test sets.
Anthology ID:
2012.amta-papers.17
Volume:
Proceedings of the 10th Conference of the Association for Machine Translation in the Americas: Research Papers
Month:
October 28-November 1
Year:
2012
Address:
San Diego, California, USA
Venue:
AMTA
SIG:
Publisher:
Association for Machine Translation in the Americas
Note:
Pages:
Language:
URL:
https://aclanthology.org/2012.amta-papers.17
DOI:
Bibkey:
Cite (ACL):
Artem Sokolov, Guillaume Wisniewski, and François Yvon. 2012. Non-linear n-best List Reranking with Few Features. In Proceedings of the 10th Conference of the Association for Machine Translation in the Americas: Research Papers, San Diego, California, USA. Association for Machine Translation in the Americas.
Cite (Informal):
Non-linear n-best List Reranking with Few Features (Sokolov et al., AMTA 2012)
Copy Citation:
PDF:
https://aclanthology.org/2012.amta-papers.17.pdf