Capturing Paradigmatic and Syntagmatic Lexical Relations: Towards Accurate Chinese Part-of-Speech Tagging

From the perspective of structural linguistics, we explore paradigmatic and syntagmatic lexical relations for Chinese POS tagging, an important and challenging task for Chinese language processing. Paradigmatic lexical relations are explicitly captured by word clustering on large-scale unlabeled data and are used to design new features to enhance a discriminative tagger. Syntagmatic lexical relations are implicitly captured by constituent parsing and are utilized via system combination. Experiments on the Penn Chinese Treebank demonstrate the importance of both paradigmatic and syntagmatic relations. Our linguistically motivated approaches yield a relative error reduction of 18% in total over a state-of-the-art baseline.

[1]  Dan Klein,et al.  Learning Accurate, Compact, and Interpretable Tree Annotation , 2006, ACL.

[2]  Lluís Màrquez i Villodre,et al.  SVMTool: A general POS Tagger Generator Based on Support Vector Machines , 2004, LREC.

[3]  M. A. R T A P A L,et al.  The Penn Chinese TreeBank: Phrase structure annotation of a large corpus , 2005, Natural Language Engineering.

[4]  Franz Josef Och,et al.  An Efficient Method for Determining Bilingual Word Classes , 1999, EACL.

[5]  Teruko Mitamura,et al.  A Fast, Accurate Deterministic Parser for Chinese , 2006, ACL.

[6]  Michael Collins,et al.  Head-Driven Statistical Models for Natural Language Parsing , 2003, CL.

[7]  Stephen Clark,et al.  Transition-Based Parsing of the Chinese Treebank using a Global Discriminative Model , 2009, IWPT.

[8]  Weiwei Sun.  Word-based and Character-based Word Segmentation Models: Comparison and Combination , 2010, COLING.

[9]  Stephen Clark,et al.  A Tale of Two Parsers: Investigating and Combining Graph-based and Transition-based Dependency Parsing , 2008, EMNLP.

[10]  Haizhou Li,et al.  Joint Models for Chinese POS Tagging and Dependency Parsing , 2011, EMNLP.

[11]  Daniel Jurafsky,et al.  Morphological features help POS tagging of unknown words across language varieties , 2005, IJCNLP.

[12]  M. I. Jordan.  Leo Breiman , 2011, 1101.0929.

[13]  Michael Collins,et al.  Discriminative Training Methods for Hidden Markov Models: Theory and Experiments with Perceptron Algorithms , 2002, EMNLP.

[14]  Kenji Sagae,et al.  Dynamic Programming for Linear-Time Incremental Parsing , 2010, ACL.

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

[16]  Dan Klein,et al.  Feature-Rich Part-of-Speech Tagging with a Cyclic Dependency Network , 2003, NAACL.

[17]  Dan Klein,et al.  Improved Inference for Unlexicalized Parsing , 2007, NAACL.

[18]  Weiwei Sun,et al.  Enhancing Chinese Word Segmentation Using Unlabeled Data , 2011, EMNLP.

[19]  Percy Liang,et al.  Semi-Supervised Learning for Natural Language , 2005 .

[20]  François Yvon,et al.  Practical Very Large Scale CRFs , 2010, ACL.

[21]  Mary P. Harper,et al.  Improving A Simple Bigram HMM Part-of-Speech Tagger by Latent Annotation and Self-Training , 2009, NAACL.

[22]  Giorgio Satta,et al.  Guided Learning for Bidirectional Sequence Classification , 2007, ACL.

[23]  Xavier Carreras,et al.  Simple Semi-supervised Dependency Parsing , 2008, ACL.

[24]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[25]  Wen Wang,et al.  Mandarin Part-of-Speech Tagging and Discriminative Reranking , 2007, EMNLP.

[26]  Jun'ichi Tsujii,et al.  Probabilistic CFG with Latent Annotations , 2005, ACL.

[27]  Scott Miller,et al.  Name Tagging with Word Clusters and Discriminative Training , 2004, NAACL.

[28]  Eugene Charniak,et al.  A Maximum-Entropy-Inspired Parser , 2000, ANLP.

[29]  Robert L. Mercer,et al.  Class-Based n-gram Models of Natural Language , 1992, CL.

[30]  Frederick Jelinek,et al.  Improved clustering techniques for class-based statistical language modeling , 1999 .

[31]  Hermann Ney,et al.  Improved clustering techniques for class-based statistical language modelling , 1993, EUROSPEECH.