论文信息 - Phrase-based Language Modelling for Statistical Machine Translation

Phrase-based Language Modelling for Statistical Machine Translation

In this paper, we present our submitted MT system for the IWSLT2014 Evaluation Campaign. We participated in the English-French translation task. In this article we focus on one of the most important component of SMT: the language model. The idea is to use a phrase-based language model. For that, sequences from the source and the target language models are retrieved and used to calculate a phrase n-gram language model. These phrases are used to rewrite the par-allel corpus which is then used to calculate a new translation model.

Abdelmajid Ben Hamadou | Kamel Smaïli | Salma Jamoussi | Achraf Ben Romdhane

[1] Maxim Khalilov. Improving target language modeling techniques for statistical machine translation , 2007 .

[2] Frédéric Bimbot,et al. Language modeling by variable length sequences: theoretical formulation and evaluation of multigrams , 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

[3] Hermann Ney,et al. A Systematic Comparison of Various Statistical Alignment Models , 2003, CL.

[4] Hermann Ney,et al. Word Triggers and the EM Algorithm , 1997, CoNLL.

[5] Sanjeev Khudanpur,et al. Lexical triggers and latent semantic analysis for cross-lingual language model adaptation , 2004, TALIP.

[6] Kamel Smaïli,et al. Statistical language modeling based on variable-length sequences , 2003, Comput. Speech Lang..

[7] Salim Roukos,et al. Bleu: a Method for Automatic Evaluation of Machine Translation , 2002, ACL.

[8] Philipp Koehn,et al. Moses: Open Source Toolkit for Statistical Machine Translation , 2007, ACL.

[9] Mauro Cettolo,et al. WIT3: Web Inventory of Transcribed and Translated Talks , 2012, EAMT.

[10] Andreas Stolcke,et al. SRILM - an extensible language modeling toolkit , 2002, INTERSPEECH.

[11] Kamel Smaïli,et al. Discovering phrases in machine translation by simulated annealing , 2008, INTERSPEECH.

[12] Ruhi Sarikaya,et al. Joint Morphological-Lexical Language Modeling for Machine Translation , 2007, NAACL.