Incremental Semantic Role Labeling with Tree Adjoining Grammar

We introduce the task of incremental semantic role labeling (iSRL), in which semantic roles are assigned to incomplete input (sentence prefixes). iSRL is the semantic equivalent of incremental parsing, and is useful for language modeling, sentence completion, machine translation, and psycholinguistic modeling. We propose an iSRL system that combines an incremental TAG parser with a semantically enriched lexicon, a role propagation algorithm, and a cascade of classifiers. Our approach achieves an SRL Fscore of 78.38% on the standard CoNLL 2009 dataset. It substantially outperforms a strong baseline that combines gold-standard syntactic dependencies with heuristic role assignment, as well as a baseline based on Nivre’s incremental dependency parser.

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

[2]  Yuji Matsumoto MaltParser: A language-independent system for data-driven dependency parsing , 2005 .

[3]  Aravind K. Joshi,et al.  Tree-adjoining grammars and lexicalized grammars , 1992, Tree Automata and Languages.

[4]  Frank Keller,et al.  A Probabilistic Model of Semantic Plausibility in Sentence Processing , 2009, Cogn. Sci..

[5]  David Chiang,et al.  Statistical Parsing with an Automatically-Extracted Tree Adjoining Grammar , 2000, ACL.

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

[7]  Chih-Jen Lin,et al.  LIBLINEAR: A Library for Large Linear Classification , 2008, J. Mach. Learn. Res..

[8]  Frank Keller,et al.  Incremental, Predictive Parsing with Psycholinguistically Motivated Tree-Adjoining Grammar , 2013, CL.

[9]  Xavier Carreras,et al.  Semantic Role Labeling: An Introduction to the Special Issue , 2008, Computational Linguistics.

[10]  Ian H. Witten,et al.  The zero-frequency problem: Estimating the probabilities of novel events in adaptive text compression , 1991, IEEE Trans. Inf. Theory.

[11]  Pierre Nugues,et al.  Multilingual Semantic Role Labeling , 2009, CoNLL Shared Task.

[12]  Anoop Sarkar,et al.  Experimental Evaluation of LTAG-Based Features for Semantic Role Labeling , 2007, EMNLP-CoNLL.

[13]  Richard Johansson,et al.  Extended Constituent-to-Dependency Conversion for English , 2007, NODALIDA.

[14]  LapataMirella,et al.  Similarity-driven semantic role induction via graph partitioning , 2014 .

[15]  Frank Keller,et al.  Incremental Tree Substitution Grammar for Parsing and Sentence Prediction , 2013, TACL.

[16]  Richard Johansson,et al.  The CoNLL-2009 Shared Task: Syntactic and Semantic Dependencies in Multiple Languages , 2009, CoNLL Shared Task.

[17]  Wolfgang Menzel,et al.  Incremental Parsing and the Evaluation of Partial Dependency Analyses , 2011 .

[18]  Fei Xia,et al.  A Uniform Method of Grammar Extraction and Its Applications , 2000, EMNLP.

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

[20]  Frank Keller,et al.  Cognitively Plausible Models of Human Language Processing , 2010, ACL.

[21]  Vincenzo Lombardo,et al.  Dynamic TAG and Lexical Dependencies , 2007 .

[22]  Matthew W. Crocker,et al.  Ambiguity Resolution in Sentence Processing: Evidence against Frequency-Based Accounts , 2000 .

[23]  Richard Johansson,et al.  The CoNLL 2008 Shared Task on Joint Parsing of Syntactic and Semantic Dependencies , 2008, CoNLL.