The Importance of Syntactic Parsing and Inference in Semantic Role Labeling

We present a general framework for semantic role labeling. The framework combines a machine-learning technique with an integer linear programming-based inference procedure, which incorporates linguistic and structural constraints into a global decision process. Within this framework, we study the role of syntactic parsing information in semantic role labeling. We show that full syntactic parsing information is, by far, most relevant in identifying the argument, especially, in the very first stagethe pruning stage. Surprisingly, the quality of the pruning stage cannot be solely determined based on its recall and precision. Instead, it depends on the characteristics of the output candidates that determine the difficulty of the downstream problems. Motivated by this observation, we propose an effective and simple approach of combining different semantic role labeling systems through joint inference, which significantly improves its performance. Our system has been evaluated in the CoNLL-2005 shared task on semantic role labeling, and achieves the highest F1 score among 19 participants.

[1]  Owen Rambow,et al.  Use of Deep Linguistic Features for the Recognition and Labeling of Semantic Arguments , 2003, EMNLP.

[2]  Michael Collins,et al.  Three Generative, Lexicalised Models for Statistical Parsing , 1997, ACL.

[3]  Dan Roth,et al.  Integer linear programming inference for conditional random fields , 2005, ICML.

[4]  Dan Roth,et al.  Generalized Inference with Multiple Semantic Role Labeling Systems , 2005, CoNLL.

[5]  Martha Palmer,et al.  From TreeBank to PropBank , 2002, LREC.

[6]  B. Levin,et al.  From Lexical Semantics to Argument Realization , 1996 .

[7]  Daniel Jurafsky,et al.  Semantic Role Chunking Combining Complementary Syntactic Views , 2005, CoNLL.

[8]  Daniel Gildea,et al.  Identifying Semantic Roles Using Combinatory Categorial Grammar , 2003, EMNLP.

[9]  Dan Roth,et al.  A Linear Programming Formulation for Global Inference in Natural Language Tasks , 2004, CoNLL.

[10]  Daniel Jurafsky,et al.  Semantic Role Labeling by Tagging Syntactic Chunks , 2004, CoNLL.

[11]  Daniel Gildea,et al.  The Necessity of Parsing for Predicate Argument Recognition , 2002, ACL.

[12]  Yoav Freund,et al.  Large Margin Classification Using the Perceptron Algorithm , 1998, COLT.

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

[14]  Christian Prins,et al.  Applications of optimisation with Xpress-MP , 2002 .

[15]  Kadri Hacioglu,et al.  Semantic Role Labeling Using Dependency Trees , 2004, COLING.

[16]  Dan Roth,et al.  A Winnow-Based Approach to Context-Sensitive Spelling Correction , 1998, Machine Learning.

[17]  John B. Lowe,et al.  The Berkeley FrameNet Project , 1998, ACL.

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

[19]  Daniel Jurafsky,et al.  Automatic Labeling of Semantic Roles , 2002, CL.

[20]  Nianwen Xue,et al.  Calibrating Features for Semantic Role Labeling , 2004, EMNLP.

[21]  Xavier Carreras,et al.  Introduction to the CoNLL-2004 Shared Task: Semantic Role Labeling , 2004, CoNLL.

[22]  Dan Roth,et al.  The Use of Classifiers in Sequential Inference , 2001, NIPS.

[23]  Daniel Gildea,et al.  The Proposition Bank: An Annotated Corpus of Semantic Roles , 2005, CL.

[24]  Dan Roth,et al.  A Sequential Model for Multi-Class Classification , 2001, EMNLP.

[25]  Dan Roth,et al.  Learning to Resolve Natural Language Ambiguities: A Unified Approach , 1998, AAAI/IAAI.

[26]  Dan Roth,et al.  Semantic Role Labeling Via Integer Linear Programming Inference , 2004, COLING.

[27]  Christopher D. Manning,et al.  A Joint Model for Semantic Role Labeling , 2005, CoNLL.

[28]  Sanda M. Harabagiu,et al.  Using Predicate-Argument Structures for Information Extraction , 2003, ACL.

[29]  Xavier Carreras,et al.  Filtering-Ranking Perceptron Learning for Partial Parsing , 2005, Machine Learning.

[30]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[31]  Dan Roth,et al.  Learning and Inference for Clause Identification , 2002, ECML.

[32]  Xavier Carreras,et al.  Online Learning via Global Feedback for Phrase Recognition , 2003, NIPS.

[33]  Dan Roth,et al.  Linear Concepts and Hidden Variables , 2004, Machine Learning.

[34]  Daniel Jurafsky,et al.  Shallow Semantic Parsing using Support Vector Machines , 2004, NAACL.

[35]  Sabine Buchholz,et al.  Introduction to the CoNLL-2000 Shared Task Chunking , 2000, CoNLL/LLL.

[36]  Beatrice Santorini,et al.  Building a Large Annotated Corpus of English: The Penn Treebank , 1993, CL.

[37]  Tong Zhang,et al.  Text Chunking based on a Generalization of Winnow , 2002, J. Mach. Learn. Res..

[38]  S. T. Buckland,et al.  Computer-Intensive Methods for Testing Hypotheses. , 1990 .

[39]  Beth Levin,et al.  English Verb Classes and Alternations: A Preliminary Investigation , 1993 .

[40]  Dan Roth,et al.  Exploring evidence for shallow parsing , 2001, CoNLL.

[41]  Eugene Charniak,et al.  Immediate-Head Parsing for Language Models , 2001, ACL.

[42]  Xavier Carreras,et al.  Introduction to the CoNLL-2005 Shared Task: Semantic Role Labeling , 2005, CoNLL.

[43]  Ido Dagan,et al.  Mistake-Driven Learning in Text Categorization , 1997, EMNLP.

[44]  Lluís Màrquez i Villodre,et al.  Semantic Role Labeling as Sequential Tagging , 2005, CoNLL.

[45]  Roser Morante,et al.  Semantic Role Labeling based on TiMBL , 2007 .

[46]  Daniel Jurafsky,et al.  Support Vector Learning for Semantic Argument Classification , 2005, Machine Learning.