Modeling lexical cohesion for document-level machine translation

Authors:
Deyi Xiong;Guosheng Ben;Min Zhang;Yajuan Lü;Qun Liu
Affiliations:
School of Computer Science and Technology, Soochow University, Suzhou, China and Institute for Infocomm Research, Connexis, Singapore;Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, China;School of Computer Science and Technology, Soochow University, Suzhou, China and Institute for Infocomm Research, Connexis, Singapore;Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, China;Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, China and Centre for Next Generation Localisation, School of Computing, Dublin City University, Ireland
Venue:
IJCAI'13 Proceedings of the Twenty-Third international joint conference on Artificial Intelligence
Year:
2013

Citing 13
Cited 0

Word association norms, mutual information, and lexicography

Computational Linguistics
Empirical estimates of adaptation: the chance of two noriegas is closer to p/2 than p2

COLING '00 Proceedings of the 18th conference on Computational linguistics - Volume 1
BLEU: a method for automatic evaluation of machine translation

ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
Minimum error rate training in statistical machine translation

ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
Hierarchical Phrase-Based Translation

Computational Linguistics
Modeling local coherence: An entity-based approach

Computational Linguistics
Context adaptation in statistical machine translation using models with exponentially decaying cache

DANLP 2010 Proceedings of the 2010 Workshop on Domain Adaptation for Natural Language Processing
Enhancing language models in statistical machine translation with backward n-grams and mutual information triggers

HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 1
Better hypothesis testing for statistical machine translation: controlling for optimizer instability

HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies: short papers - Volume 2
Cache-based document-level statistical machine translation

EMNLP '11 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Encouraging consistent translation choices

NAACL HLT '12 Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Extending machine translation evaluation metrics with lexical cohesion to document level

EMNLP-CoNLL '12 Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning
Document-wide decoding for phrase-based statistical machine translation

EMNLP-CoNLL '12 Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning

Quantified Score

Hi-index	0.00

Visualization

Abstract

Lexical cohesion arises from a chain of lexical items that establish links between sentences in a text. In this paper we propose three different models to capture lexical cohesion for document-level machine translation: (a) a direct reward model where translation hypotheses are rewarded whenever lexical cohesion devices occur in them, (b) a conditional probability model where the appropriateness of using lexical cohesion devices is measured, and (c) a mutual information trigger model where a lexical cohesion relation is considered as a trigger pair and the strength of the association between the trigger and the triggered item is estimated by mutual information. We integrate the three models into hierarchical phrase-based machine translation and evaluate their effectiveness on the NIST Chinese-English translation tasks with large-scale training data. Experiment results show that all three models can achieve substantial improvements over the baseline and that the mutual information trigger model performs better than the others.