A Global Joint Model for Semantic Role Labeling

We present a model for semantic role labeling that effectively captures the linguistic intuition that a semantic argument frame is a joint structure, with strong dependencies among the arguments. We show how to incorporate these strong dependencies in a statistical joint model with a rich set of features over multiple argument phrases. The proposed model substantially outperforms a similar state-of-the-art local model that does not include dependencies among different arguments. We evaluate the gains from incorporating this joint information on the Propbank corpus, when using correct syntactic parse trees as input, and when using automatically derived parse trees. The gains amount to 24.1% error reduction on all arguments and 36.8% on core arguments for gold-standard parse trees on Propbank. For automatic parse trees, the error reductions are 8.3% and 10.3% on all and core arguments, respectively. We also present results on the CoNLL 2005 shared task data set. Additionally, we explore considering multiple syntactic analyses to cope with parser noise and uncertainty.

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

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

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

[4]  Kadri Hacioglu.  A lightweight semantic chunking model based on tagging , 2004, HLT-NAACL 2004.

[5]  Andrew McCallum,et al.  Maximum Entropy Markov Models for Information Extraction and Segmentation , 2000, ICML.

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

[7]  Andrew Y. Ng,et al.  Solving the Problem of Cascading Errors: Approximate Bayesian Inference for Linguistic Annotation Pipelines , 2006, EMNLP.

[8]  Douglas Roland,et al.  Verb Sense and Verb Subcategorization Probabilities , 2001 .

[9]  Martha Palmer,et al.  The Integration of Syntactic Parsing and Semantic Role Labeling , 2005, CoNLL.

[10]  Phil Blunsom,et al.  Semantic Role Labelling with Tree Conditional Random Fields , 2005, CoNLL.

[11]  Mihai Surdeanu,et al.  A Robust Combination Strategy for Semantic Role Labeling , 2005, HLT.

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

[13]  Dan Roth,et al.  Semantic Role Labeling Via Generalized Inference Over Classifiers , 2004, CoNLL.

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

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

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

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

[18]  Dan Roth,et al.  The Necessity of Syntactic Parsing for Semantic Role Labeling , 2005, IJCAI.

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

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

[21]  Daniel Jurafsky,et al.  Semantic Role Labeling Using Different Syntactic Views , 2005, ACL.

[22]  Daniel Gildea,et al.  Automatic Labeling of Semantic Roles , 2000, ACL.

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

[24]  Roger Levy,et al.  Deep Dependencies from Context-Free Statistical Parsers: Correcting the Surface Dependency Approximation , 2004, ACL.

[25]  Fernando Pereira,et al.  Shallow Parsing with Conditional Random Fields , 2003, NAACL.

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

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