Paraphrase lattice for statistical machine translation

Authors:
Takashi Onishi;Masao Utiyama;Eiichiro Sumita
Affiliations:
National Institute of Information and Communications Technology, Keihanna Science City, Kyoto, Japan;National Institute of Information and Communications Technology, Keihanna Science City, Kyoto, Japan;National Institute of Information and Communications Technology, Keihanna Science City, Kyoto, Japan
Venue:
ACLShort '10 Proceedings of the ACL 2010 Conference Short Papers
Year:
2010

Citing 7
Cited 9

Minimum error rate training in statistical machine translation

ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
Paraphrasing with bilingual parallel corpora

ACL '05 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics
Improved statistical machine translation using paraphrases

HLT-NAACL '06 Proceedings of the main conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics
Moses: open source toolkit for statistical machine translation

ACL '07 Proceedings of the 45th Annual Meeting of the ACL on Interactive Poster and Demonstration Sessions
Improved Statistical Machine Translation Using Monolingual Paraphrases

Proceedings of the 2008 conference on ECAI 2008: 18th European Conference on Artificial Intelligence
Using a maximum entropy model to build segmentation lattices for MT

NAACL '09 Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Improved statistical machine translation using monolingually-derived paraphrases

EMNLP '09 Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 1 - Volume 1

Example-based paraphrasing for improved phrase-based statistical machine translation

EMNLP '10 Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing
Incorporating source-language paraphrases into phrase-based SMT with confusion networks

SSST-5 Proceedings of the Fifth Workshop on Syntax, Semantics and Structure in Statistical Translation
Web-based validation for contextual targeted paraphrasing

MTTG '11 Proceedings of the Workshop on Monolingual Text-To-Text Generation
Filtering antonymous, trend-contrasting, and polarity-dissimilar distributional paraphrases for improving statistical machine translation

WMT '11 Proceedings of the Sixth Workshop on Statistical Machine Translation
Power-law distributions for paraphrases extracted from bilingual corpora

EACL '12 Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics
Improve SMT quality with automatically extracted paraphrase rules

ACL '12 Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers - Volume 1
Phrase model training for statistical machine translation with word lattices of preprocessing alternatives

WMT '12 Proceedings of the Seventh Workshop on Statistical Machine Translation
A-STAR: Toward translating Asian spoken languages

Computer Speech and Language
Distributional phrasal paraphrase generation for statistical machine translation

ACM Transactions on Intelligent Systems and Technology (TIST) - Special Sections on Paraphrasing; Intelligent Systems for Socially Aware Computing; Social Computing, Behavioral-Cultural Modeling, and Prediction

Quantified Score

Hi-index	0.00

Visualization

Abstract

Lattice decoding in statistical machine translation (SMT) is useful in speech translation and in the translation of German because it can handle input ambiguities such as speech recognition ambiguities and German word segmentation ambiguities. We show that lattice decoding is also useful for handling input variations. Given an input sentence, we build a lattice which represents paraphrases of the input sentence. We call this a paraphrase lattice. Then, we give the paraphrase lattice as an input to the lattice decoder. The decoder selects the best path for decoding. Using these paraphrase lattices as inputs, we obtained significant gains in BLEU scores for IWSLT and Europarl datasets.