You have already added 0 works in your ORCID record related to the merged Research product.
You have already added 0 works in your ORCID record related to the merged Research product.
Modelling Pronominal Anaphora in Statistical Machine Translation
Modelling Pronominal Anaphora in Statistical Machine Translation
Current Statistical Machine Translation (SMT) systems translate texts sentence by sentence without considering any cross-sentential context. Assuming independence between sentences makes it difficult to take certain translation decisions when the necessary information cannot be determined locally. We argue for the necessity to include cross-sentence dependencies in SMT. As a case in point, we study the problem of pronominal anaphora translation by manually evaluating German-English SMT output. We then present a word dependency model for SMT, which can represent links between word pairs in the same or in different sentences. We use this model to integrate the output of a coreference resol- ution system into English-German SMT with a view to improving the translation of anaphoric pronouns.
- Uppsala University Sweden
- University of Edinburgh United Kingdom
Språkteknologi (språkvetenskaplig databehandling), Language Technology (Computational Linguistics)
Språkteknologi (språkvetenskaplig databehandling), Language Technology (Computational Linguistics)
1512
[1] P. F. Brown, J. Cocke, S. A. Della Pietra, V. J. Della Pietra, et al., A“ statistical approach to Machine Translation,” Computational linguistics, vol. 16, pp. 79-85, 1990.
[2] P. F. Brown, S. A. Della Pietra, V. J. Della Pietra, and R. L. Mercer, “The mathematics of Statistical Machine Translation,” Computational linguistics, vol. 19, pp. 263-311, 1993.
[3] M. Strube, A“naphora and coreference resolution, Statistical,” in Encyclopedia of language and linguistics. Elsevier, 2006, pp. 216-222.
[4] C. Callison-Burch, P. Koehn, C. Monz, and J. Schroeder, “Findings of the 2009 Workshop on Statistical Machine Translation,” in Proceedings of the Fourth Workshop on Statistical Machine Translation. Athens, Greece: Association for Computational Linguistics, March 2009, pp. 1-28.
[5] C. Hardmeier, A. Bisazza, and M. Federico, “FBK at WMT 2010: Word lattices for morphological reduction and chunk-based reordering,” in Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and Metrics MATR. Uppsala, Sweden: Association for Computational Linguistics, 2010. [OpenAIRE]
[6] R. Mitkov, “Introduction: Special issue on anaphora resolution in Machine Translation and Multilingual NLP,” Machine translation, vol. 14, pp. 159-161, 1999.
[7] R. Le Nagard and P. Koehn, A“iding pronoun translation with co-reference resolution,” in Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR. Uppsala, Sweden: Association for Computational Linguistics, July 2010, pp. 252-261. [OpenAIRE]
[8] S. Broscheit, M. Poesio, S. P. Ponzetto, K. Joseba Rodriguez, L. Romano, O. Uryupina, Y. Versley, and R. Zanoli, “BART: A multilingual anaphora resolution system,” in Proceedings of the 5th International Workshop on Semantic Evaluations (SemEval-2010), Uppsala, Sweden, 15-16 July 2010, 2010.
[9] P. Koehn, H. Hoang, A. Birch, et al., “Moses: open source toolkit for Statistical Machine Translation,” in Annual meeting of the Association for Computational Linguistics: Demonstration session, Prague, 2007, pp. 177-180.
[10] F. J. Och and H. Ney, “Discriminative training and maximum entropy models for Statistical Machine Translation,” in Proceedings of the 40th annual meeting of the Association for Computational Linguistics, Philadelphia, 2002, pp. 295-302.
- 1
- 2
citations This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).0 popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.Average influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).Average impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.Average citations This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).0 popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.Average influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).Average impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.Average
Citations provided by BIP!Popularity provided by BIP!- Uppsala University Sweden
- University of Edinburgh United Kingdom
Current Statistical Machine Translation (SMT) systems translate texts sentence by sentence without considering any cross-sentential context. Assuming independence between sentences makes it difficult to take certain translation decisions when the necessary information cannot be determined locally. We argue for the necessity to include cross-sentence dependencies in SMT. As a case in point, we study the problem of pronominal anaphora translation by manually evaluating German-English SMT output. We then present a word dependency model for SMT, which can represent links between word pairs in the same or in different sentences. We use this model to integrate the output of a coreference resol- ution system into English-German SMT with a view to improving the translation of anaphoric pronouns.