Chinese word segmentation and statistical machine translation

Chinese word segmentation (CWS) is a necessary step in Chinese-English statistical machine translation (SMT) and its performance has an impact on the results of SMT. However, there are many choices involved in creating a CWS system such as various specifications and CWS methods. The choices made will create a new CWS scheme, but whether it will produce a superior or inferior translation has remained unknown to date. This article examines the relationship between CWS and SMT. The effects of CWS on SMT were investigated using different specifications and CWS methods. Four specifications were selected for investigation: Beijing University (PKU), Hong Kong City University (CITYU), Microsoft Research (MSR), and Academia SINICA (AS). We created 16 CWS schemes under different settings to examine the relationship between CWS and SMT. Our experimental results showed that the MSR's specifications produced the lowest quality translations. In examining the effects of CWS methods, we tested dictionary-based and CRF-based approaches and found there was no significant difference between the two in the quality of the resulting translations. We also found the correlation between the CWS F-score and SMT BLEU score was very weak. We analyzed CWS errors and their effect on SMT by evaluating systems trained with and without these errors. This article also proposes two methods for combining advantages of different specifications: a simple concatenation of training data and a feature interpolation approach in which the same types of features of translation models from various CWS schemes are linearly interpolated. We found these approaches were very effective in improving the quality of translations.

[1]  Yuji Matsumoto,et al.  Chunking with Support Vector Machines , 2001, NAACL.

[2]  Eiichiro Sumita,et al.  Subword-based Tagging by Conditional Random Fields for Chinese Word Segmentation , 2006, NAACL.

[3]  Qun Liu,et al.  HHMM-based Chinese Lexical Analyzer ICTCLAS , 2003, SIGHAN.

[4]  Nizar Habash,et al.  Combination of Arabic Preprocessing Schemes for Statistical Machine Translation , 2006, ACL.

[5]  Young-Suk Lee,et al.  Morphological Analysis for Statistical Machine Translation , 2004, NAACL.

[6]  Michael Paul,et al.  Overview of the IWSLT06 evaluation campaign , 2006, IWSLT.

[7]  Andrew McCallum,et al.  Chinese Segmentation and New Word Detection using Conditional Random Fields , 2004, COLING.

[8]  Roland Kuhn,et al.  Mixture-Model Adaptation for SMT , 2007, WMT@ACL.

[9]  Jianfeng Gao,et al.  Adaptive Chinese Word Segmentation , 2004, ACL.

[10]  Daniel Jurafsky,et al.  A Conditional Random Field Word Segmenter for Sighan Bakeoff 2005 , 2005, IJCNLP.

[11]  Ying Zhang,et al.  Interpreting BLEU/NIST Scores: How Much Improvement do We Need to Have a Better System? , 2004, LREC.

[12]  Eiichiro Sumita,et al.  Chinese Unknown Word Translation by Subword Re-segmentation , 2008, IJCNLP.

[13]  Daniel Marcu,et al.  Statistical Phrase-Based Translation , 2003, NAACL.

[14]  Sharon Goldwater,et al.  Improving Statistical MT through Morphological Analysis , 2005, HLT.

[15]  Franz Josef Och,et al.  Minimum Error Rate Training in Statistical Machine Translation , 2003, ACL.

[16]  Andrew McCallum,et al.  Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data , 2001, ICML.

[17]  Philipp Koehn,et al.  Edinburgh System Descriptionfor the 2005 NIST MT Evaluation , 2005 .

[18]  Hermann Ney,et al.  Using POS information for statistical machine translation into morphologically rich languages , 2003, Proceedings of the tenth conference on European chapter of the Association for Computational Linguistics - EACL '03.

[19]  Thomas Emerson,et al.  The Second International Chinese Word Segmentation Bakeoff , 2005, IJCNLP.

[20]  Nianwen Xue,et al.  Chinese Word Segmentation as LMR Tagging , 2003, SIGHAN.

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

[22]  Alexander M. Fraser,et al.  Squibs and Discussions: Measuring Word Alignment Quality for Statistical Machine Translation , 2007, CL.

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

[24]  SumitaEiichiro,et al.  Chinese word segmentation and statistical machine translation , 2008 .