Syntax-based reordering for statistical machine translation

► A syntax-driven approach to handling the problem of word ordering for statistical machine translation. ► The word order challenge is alleviated including morpho-syntactical and statistical information in the context of a pre-translation reordering framework. ► The results are presented for small a...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Computer speech & language Ročník 25; číslo 4; s. 761 - 788
Hlavní autoři:	Khalilov, Maxim, Fonollosa, José A.R.
Médium:	Journal Article Publikace
Jazyk:	angličtina
Vydáno:	Kidlington Elsevier Ltd 01.10.2011 Elsevier
Témata:	Applied linguistics Computational Linguistics Distortion Informàtica Intel·ligència artificial Linguistics Lingüística computacional Llenguatge natural Machine Translation Mathematical models Natural Language Processing Speech Statistical Analysis Statistical machine translation Syntax Tasks Tractament del llenguatge natural (Informàtica) Training Translation Translations Word Order Word reordering Àrees temàtiques de la UPC Word reordering Natural language processing Computational linguistics Statistical machine translation Word order Syntax Machine translation Statistics
ISSN:	0885-2308, 1095-8363
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	► A syntax-driven approach to handling the problem of word ordering for statistical machine translation. ► The word order challenge is alleviated including morpho-syntactical and statistical information in the context of a pre-translation reordering framework. ► The results are presented for small and large Chinese-to-English and Arabic-to-English translation tasks. ► The experiments are carried out on phrase-based and N-gram-based statistical machine translation systems. In this paper, we develop an approach called syntax-based reordering (SBR) to handling the fundamental problem of word ordering for statistical machine translation (SMT). We propose to alleviate the word order challenge including morpho-syntactical and statistical information in the context of a pre-translation reordering framework aimed at capturing short- and long-distance word distortion dependencies. We examine the proposed approach from the theoretical and experimental points of view discussing and analyzing its advantages and limitations in comparison with some of the state-of-the-art reordering methods. In the final part of the paper, we describe the results of applying the syntax-based model to translation tasks with a great need for reordering (Chinese-to-English and Arabic-to-English). The experiments are carried out on standard phrase-based and alternative N-gram-based SMT systems. We first investigate sparse training data scenarios, in which the translation and reordering models are trained on a sparse bilingual data, then scaling the method to a large training set and demonstrating that the improvement in terms of translation quality is maintained.
Bibliografie:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 ObjectType-Article-2 ObjectType-Feature-1
ISSN:	0885-2308 1095-8363
DOI:	10.1016/j.csl.2011.01.001