Combination Strategies for Semantic Role Labeling

• Published in: The Journal of artificial intelligence research 2007-01, Vol.29, p.105-151
• Main Authors: Surdeanu, M., Marquez, L., Carreras, X., Comas, P. R.
• Format: Article
• Language: English
• Subjects: Artificial intelligence; Classifiers; Constraint modelling; Evaluation; Inference; Labeling; Learning; Semantics
• ISSN: 1076-9757; 1076-9757; 1943-5037
• DOI: 10.1613/jair.2088

This paper introduces and analyzes a battery of inference models for the problem of semantic role labeling: one based on constraint satisfaction, and several strategies that model the inference as a meta-learning problem using discriminative classifiers. These classifiers are developed with a rich set of novel features that encode proposition and sentence-level information. To our knowledge, this is the first work that: (a) performs a thorough analysis of learning-based inference models for semantic role labeling, and (b) compares several inference strategies in this context. We evaluate the proposed inference strategies in the framework of the CoNLL-2005 shared task using only automatically-generated syntactic information. The extensive experimental evaluation and analysis indicates that all the proposed inference strategies are successful -they all outperform the current best results reported in the CoNLL-2005 evaluation exercise- but each of the proposed approaches has its advantages and disadvantages. Several important traits of a state-of-the-art SRL combination strategy emerge from this analysis: (i) individual models should be combined at the granularity of candidate arguments rather than at the granularity of complete solutions; (ii) the best combination strategy uses an inference model based in learning; and (iii) the learning-based inference benefits from max-margin classifiers and global feedback.