Trait-based hypothesis selection for machine translation

Authors:
Jacob Devlin;Spyros Matsoukas
Affiliations:
Raytheon BBN Technologies, Cambridge, MA;Raytheon BBN Technologies, Cambridge, MA
Venue:
NAACL HLT '12 Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Year:
2012

Citing 7
Cited 0

Hierarchical Phrase-Based Translation

Computational Linguistics
11,001 new features for statistical machine translation

NAACL '09 Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Minimum Bayes risk combination of translation hypotheses from alternative morphological decompositions

NAACL-Short '09 Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Companion Volume: Short Papers
Variational decoding for statistical machine translation

ACL '09 Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP: Volume 2 - Volume 2
Consensus training for consensus decoding in machine translation

EMNLP '09 Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 3 - Volume 3
BBN system description for WMT10 system combination task

WMT '10 Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR
Combining unsupervised and supervised alignments for MT: an empirical study

EMNLP '10 Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

In the area of machine translation (MT) system combination, previous work on generating input hypotheses has focused on varying a core aspect of the MT system, such as the decoding algorithm or alignment algorithm. In this paper, we propose a new method for generating diverse hypotheses from a single MT system using traits. These traits are simple properties of the MT output such as "average output length" and "average rule length." Our method is designed to select hypotheses which vary in trait value but do not significantly degrade in BLEU score. These hypotheses can be combined using standard system combination techniques to produce a 1.2-1.5 BLEU gain on the Arabic-English NIST MT06/MT08 translation task.