Shouxun Lin

Shouxun Lin

Auto-generated profile, based on publicly available information

Shouxun Lin

Chinese Academy of Sciences

Research Focus & Metrics

Academic Career Length

23Years (2004-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2006
Verified
Conference Paper
Open access
PDF file
DXDeyi Xiong
Deyi Xiong
QLQun Liu
Qun Liu
SLShouxun Lin
Shouxun Lin
We propose a novel reordering model for phrase-based statistical machine translation (SMT) that uses a maximum entropy (MaxEnt) model to predicate reorderings of neighbor blocks (phrase pairs). The model provides content-dependent, hierarchical phrasal reordering with generalization based on features automatically learned from a real-world bitext. We present an algorithm to extract all reordering events of neighbor blocks from bilingual data. In our experiments on Chinese-to-English translation, this MaxEnt-based reordering model obtains significant improvements in BLEU score on the NIST MT-05 and IWSLT-04 tasks.

1 September 2010 in Computational Linguistics
Verified
Journal Article
Open access
YLYang Liu
Yang Liu
QLQun Liu
Qun Liu
SLShouxun Lin
Shouxun Lin
Word alignment plays an important role in many NLP tasks as it indicates the correspondence between words in a parallel text. Although widely used to align large bilingual corpora, generative models are hard to extend to incorporate arbitrary useful linguistic information. This article presents a discriminative framework for word alignment based on a linear model. Within this framework, all knowledge sources are treated as feature functions, which depend on a source language sentence, a target language sentence, and the alignment between them. We describe a number of features that could produce symmetric alignments. Our model is easy to extend and can be optimized with respect to evaluation metrics directly. The model achieves state-of-the-art alignment quality on three word alignment shared tasks for five language pairs with varying divergence and richness of resources. We further show that our approach improves translation performance for various statistical machine translation systems.

6 December 2006 in Journal of Visual Communication and Image Representation
Verified
Journal Article
Closed access
DZDongming Zhang
Dongming Zhang
SLShouxun Lin
Shouxun Lin
YZYongdong Zhang
Yongdong Zhang
LYLejun Yu
Lejun Yu

11 February 2011 in Multimedia Tools and Applications
Verified
Journal Article
Closed access
PDF file
YSYan Song
Yan Song
STSheng Tang
Sheng Tang
YZYan-Tao Zheng
Yan-Tao Zheng
TCTat-Seng Chua
Tat-Seng Chua
YZYongdong Zhang
Yongdong Zhang
SLShouxun Lin
Shouxun Lin

11 September 2009 in Chinese Journal of Computers
Verified
Journal Article
Closed access
WYWu Yuan
Wu Yuan
SLShou-Xun Lin
Shou-Xun Lin
ZNZhen-Dong Niu
Zhen-Dong Niu
HLHai-Yong Luo
Hai-Yong Luo
YZYong-Dong Zhang
Yong-Dong Zhang

1 December 2004 in Journal of Computer Science and Technology
Verified
Journal Article
Closed access
PDF file
FWFei Wang
Fei Wang
JLJin-Tao Li
Jin-Tao Li
YZYong-Dong Zhang
Yong-Dong Zhang
SLShou-Xun Lin
Shou-Xun Lin