论文信息 - A Preliminary Study on the Robustness and Generalization of Role Sets for Semantic Role Labeling

A Preliminary Study on the Robustness and Generalization of Role Sets for Semantic Role Labeling

Most Semantic Role Labeling (SRL) systems rely on available annotated corpora, being PropBank the most widely used corpus so far. Propbank role set is based on theory-neutral numbered arguments, which are linked to fine grained verb-dependant semantic roles through the verb framesets. Recently, thematic roles from the computational verb lexicon VerbNet have been suggested to be more adequate for generalization and portability of SRL systems, since they represent a compact set of verb-independent general roles widely used in linguistic theory. Such thematic roles could also put SRL systems closer to application needs. This paper presents a comparative study of the behavior of a state-of-theart SRL system on both role role sets based on the SemEval-2007 English dataset, which comprises the 50 most frequent verbs in PropBank.

Eneko Agirre | Lluís Màrquez i Villodre | Beñat Zapirain | Eneko Agirre | B. Zapirain

[1] Martha Palmer,et al. Class-Based Construction of a Verb Lexicon , 2000, AAAI/IAAI.

[2] Mihai Surdeanu,et al. Combination Strategies for Semantic Role Labeling , 2007, J. Artif. Intell. Res..

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

[4] Eneko Agirre,et al. UBC-UPC: Sequential SRL Using Selectional Preferences. An approach with Maximum Entropy Markov Models , 2007, SemEval@ACL.

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

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

[7] Martha Palmer,et al. SemEval-2007 Task-17: English Lexical Sample, SRL and All Words , 2007, Fourth International Workshop on Semantic Evaluations (SemEval-2007).

[8] Eneko Agirre,et al. Sequential SRL Using Selectional Preferences . An aproach with Maximum Entropy Markov Models , .

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

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

[11] Martha Palmer,et al. Can Semantic Roles Generalize Across Genres? , 2007, NAACL.

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

[13] Martha Palmer,et al. Combining Lexical Resources: Mapping Between PropBank and VerbNet , 2006 .