Parse Reranking Based on Higher-Order Lexical Dependencies

Existing work shows that lexical dependencies are helpful for constituent tree parsing. However, only first-order lexical dependencies have been employed and investigated in previous work. In this paper, we propose a method to employing higher-order 1 lexical dependencies for constituent tree evaluation. Our method is based on a parse reranking framework, which provides a constrained search space (via N-best lists or parse forests) and enables our parser to employ relatively complicated dependency features. We evaluate our models on the Penn Chinese Treebank. The highest F1

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

[2]  Alon Lavie,et al.  Parser Combination by Reparsing , 2006, NAACL.

[3]  Brian Roark,et al.  Incremental Parsing with the Perceptron Algorithm , 2004, ACL.

[4]  Daniel M. Bikel,et al.  Intricacies of Collins’ Parsing Model , 2004, CL.

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

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

[7]  Liang Huang,et al.  Forest Reranking: Discriminative Parsing with Non-Local Features , 2008, ACL.

[8]  Michael Collins,et al.  Discriminative Reranking for Natural Language Parsing , 2000, CL.

[9]  Haizhou Li,et al.  K-Best Combination of Syntactic Parsers , 2009, EMNLP.

[10]  Yuji Matsumoto,et al.  Statistical Dependency Analysis with Support Vector Machines , 2003, IWPT.

[11]  Dan Klein,et al.  Accurate Unlexicalized Parsing , 2003, ACL.

[12]  Chengqing Zong,et al.  Phrase Structure Parsing with Dependency Structure , 2010, COLING.

[13]  Mary P. Harper,et al.  Self-Training PCFG Grammars with Latent Annotations Across Languages , 2009, EMNLP.

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

[15]  James H. Martin,et al.  Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition , 2000 .

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

[17]  Michael Collins,et al.  Efficient Third-Order Dependency Parsers , 2010, ACL.

[18]  David Chiang,et al.  Better k-best Parsing , 2005, IWPT.

[19]  Eugene Charniak,et al.  Coarse-to-Fine n-Best Parsing and MaxEnt Discriminative Reranking , 2005, ACL.

[20]  Joakim Nivre,et al.  A Hybrid Constituency-Dependency Parser for Swedish , 2007, NODALIDA.

[21]  Joakim Nivre,et al.  A Dependency-Driven Parser for German Dependency and Constituency Representations , 2008, ACL 2008.

[22]  Fernando Pereira,et al.  Online Learning of Approximate Dependency Parsing Algorithms , 2006, EACL.

[23]  Kevin Knight,et al.  Combining Constituent Parsers , 2009, NAACL.

[24]  Michael Collins,et al.  A New Statistical Parser Based on Bigram Lexical Dependencies , 1996, ACL.

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

[26]  Yi Zhang,et al.  Hybrid Constituent and Dependency Parsing with Tsinghua Chinese Treebank , 2010, LREC.

[27]  Koby Crammer,et al.  Online Large-Margin Training of Dependency Parsers , 2005, ACL.

[28]  Dan Klein,et al.  Fast Exact Inference with a Factored Model for Natural Language Parsing , 2002, NIPS.

[29]  Fei Xia,et al.  Converting Dependency Structures to Phrase Structures , 2001, HLT.

[30]  Dan Klein,et al.  Two Languages are Better than One (for Syntactic Parsing) , 2008, EMNLP.

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

[32]  Zheng-Yu Niu,et al.  Exploiting Heterogeneous Treebanks for Parsing , 2009, ACL/IJCNLP.