Solving Hard Coreference Problems
Haoruo Peng, Daniel Khashabi, Dan Roth · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · 2015
Coreference resolution is a key problem in natural language understanding that still escapes reliable solutions.One fundamental difficulty has been that of resolving instances involving pronouns since they often require deep language understanding and use of background knowledge.In this paper we propose an algorithmic solution that involves a new representation for the knowledge required to address hard coreference problems, along with a constrained optimization framework that uses this knowledge in coreference decision making.Our representation, Predicate Schemas, is instantiated with knowledge acquired in an unsupervised way, and is compiled automatically into constraints that impact the coreference decision.We present a general coreference resolution system that significantly improves state-of-the-art performance on hard, Winograd-style, pronoun resolution cases, while still performing at the stateof-the-art level on standard coreference resolution datasets.
Cited by 80 works. doi:10.3115/v1/n15-1082 Open-access PDF
Authors
References
- Understanding natural language
- The Winograd Schema Challenge
- A model-theoretic coreference scoring scheme
- The Use of Classifiers in Sequential Inference
- An algorithm for pronominal anaphora resolution
- A Machine Learning Approach to Coreference Resolution of Noun Phrases
- Improving machine learning approaches to coreference resolution
- Resolving pronoun references
- CoNLL-2012 Shared Task: Modeling Multilingual Unrestricted Coreference in OntoNotes
- A Linear Programming Formulation for Global Inference in Natural Language Tasks