Catalogue search • Linguistik portal • Fachinformationsdienst (FID)

1	Sentence similarity-based source context modelling in PBSMT
	Haque, Rejwanul; Kumar Naskar, Sudip; Way, Andy; Costa-Jussá, Marta; Banchs, Rafael E.
	In: Haque, Rejwanul orcid:0000-0003-1680-0099 , Kumar Naskar, Sudip, Way, Andy orcid:0000-0001-5736-5930 , Costa-Jussá, Marta and Banchs, Rafael E. (2010) Sentence similarity-based source context modelling in PBSMT. In: the International Conference on Asian Language Processing 2010, 28-30 Dec. 2010, Harbin, China. (2010)
	Abstract: Target phrase selection, a crucial component of the state-of-the-art phrase-based statistical machine translation (PBSMT) model, plays a key role in generating accurate translation hypotheses. Inspired by context-rich word-sense disambiguation techniques, machine translation (MT) researchers have successfully integrated various types of source language context into the PBSMT model to improve target phrase selection. Among the various types of lexical and syntactic features, lexical syntactic descriptions in the form of supertags that preserve long-range word-to-word dependencies in a sentence have proven to be effective. These rich contextual features are able to disambiguate a source phrase, on the basis of the local syntactic behaviour of that phrase. In addition to local contextual information, global contextual information such as the grammatical structure of a sentence, sentence length and n-gram word sequences could provide additional important information to enhance this phrase-sense disambiguation. In this work, we explore various sentence similarity features by measuring similarity between a source sentence to be translated with the source-side of the bilingual training sentences and integrate them directly into the PBSMT model. We performed experiments on an English-to-Chinese translation task by applying sentence-similarity features both individually, and collaboratively with supertag-based features. We evaluate the performance of our approach and report a statistically significant relative improvement of 5.25% BLEU score when adding a sentence-similarity feature together with a supertag-based feature.
	Keyword: Machine translating; sentence similarity; source context information; statistical machine translation
	URL: http://doras.dcu.ie/16158/
	BASE
	Hide details

2	Supertags as source language context in hierarchical phrase-based SMT
	Haque, Rejwanul; Kumar Naskar, Sudip; van den Bosch, Antal...
	In: Haque, Rejwanul orcid:0000-0003-1680-0099 , Kumar Naskar, Sudip, van den Bosch, Antal and Way, Andy orcid:0000-0001-5736-5930 (2010) Supertags as source language context in hierarchical phrase-based SMT. In: AMTA 2010 - 9th Conference of the Association for Machine Translation in the Americas, 31 October - 4 November 2010, Denver, CO, USA. (2010)
	BASE
	Show details

3	MATREX: the DCU MT system for WMT 2010
	Way, Andy; Du, Jinhua; Srivastava, Ankit Kumar...
	In: Penkale, Sergio, Haque, Rejwanul orcid:0000-0003-1680-0099 , Dandapat, Sandipan, Banerjee, Pratyush, Srivastava, Ankit Kumar, Du, Jinhua orcid:0000-0002-3267-4881 , Pecina, Pavel, Kumar Naskar, Sudip, Forcada, Mikel and Way, Andy orcid:0000-0001-5736-5930 (2010) MATREX: the DCU MT system for WMT 2010. In: WMT 2010 - The Joint Fifth Workshop on Statistical Machine Translation and Metrics MATR, ACL 2010., 15-16 July 2010, Uppsala, Sweden. (2010)
	BASE
	Show details

Search in the Catalogues and Directories