Improving Reordering Models with Phrase Number Feature for Statistical Machine Translation

被引：0

作者：

Noormohammadi, Neda ^{[1
]}

Rahimi, Zahra ^{[1
]}

Khadivi, Shahram ^{[1
]}

机构：

[1] Amirkabir Univ Technol, Human Language Technol Lab, Tehran, Iran

来源：

ARTIFICIAL INTELLIGENCE AND SIGNAL PROCESSING, AISP 2013 | 2014年 / 427卷

关键词：

Statistical machine translation; Reordering model; Lexicalized reordering model; Phrase number feature; Distance based reordering model; Reordering graph;

D O I：

10.1007/978-3-319-10849-0_23

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Reordering models in statistical machine translation are crucial for many language pairs. Specifically those with very different sentence structure like Persian and English. In this paper, we enhance the well-known lexical model by taking into account the position of the phrase in the target language. We observe over 1.7 percent relative improvement in BLEU score when comparing the baseline lexical reordering model with the proposed model in an English-Persian task.

引用

页码：227 / 233

页数：7

共 14 条

[1]

Al-Onaizan Y, 2006, COLING/ACL 2006, VOLS 1 AND 2, PROCEEDINGS OF THE CONFERENCE, P529

[2]

[Anonymous], P WORKSH STAT MACH T

[3]

[Anonymous], P IWSLT

[4]

[Anonymous], 2008, Proceedings of the Conference on Empirical Methods in Natural Language Processing

[5]

[Anonymous], P ACL 2010

[6]

Knight K, 1999, COMPUT LINGUIST, V25, P607

[7]

Koehn P, 2003, HLT-NAACL 2003: HUMAN LANGUAGE TECHNOLOGY CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, PROCEEDINGS OF THE MAIN CONFERENCE, P127

[8]

Koehn P., 2007, MOSES OPEN SOURCE TO

[9]

Kopru S., 2010, AMTA 9 C ASS MACH TR

[10]

Och FJ, 2003, 41ST ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, PROCEEDINGS OF THE CONFERENCE, P160

← 1 2 →