Solving Hard Coreference Problems

Human Language Technologies: The 2015 Annual Conference of the North American Chapter of the ACL, pages 809–819, Denver, Colorado, May 31 – June 5, 2015. c⃝2015 Association for Computational Linguistics Solving Hard Coreference Problems Haoruo Peng∗ and Daniel Khashabi∗ and Dan Roth University of Illinois, Urbana-Champaign Urbana, IL, 61801 {hpeng7,khashab2,danr}@illinois.edu Abstract Coreference resolution is a key problem in natural language understanding that still es- capes reliable solutions. One fundamental dif- ficulty has been that of resolving instances involving pronouns since they often require deep language understanding and use of back- ground knowledge. In this paper we pro- pose 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 de- cision making. Our representation, Predicate Schemas, is instantiated with knowledge ac- quired in an unsupervised way, and is com- piled automatically into constraints that im- pact the coreference decision. We present a general coreference resolution system that significantly improves state-of-the-art perfor- mance on hard, Winograd-style, pronoun reso- lution cases, while still performing at the state- of-the-art level on standard coreference reso- lution datasets. 1 Introduction Coreference resolution is one of the most impor- tant tasks in Natural Language Processing (NLP). Although there is a plethora of works on this task (Soon et al., 2001a; Ng and Cardie, 2002a; Ng, 2004; Bengtson and Roth, 2008; Pradhan et al., 2012; Kummerfeld and Klein, 2013; Chang et al., 2013), it is still deemed an unsolved problem due to intricate and ambiguous nature of natural language ∗These authors contributed equally to this work. text. Existing methods perform particularly poorly on pronouns, specifically when gender or plurality information cannot help. In this paper, we aim to improve coreference resolution by addressing these hard problems. Consider the following examples: Ex.1 [A bird]e1 perched on the [limb]e2 and [it]pro bent. Ex.2 [Robert]e1 was robbed by [Kevin]e2, and [he]pro is arrested by police. In both examples, one cannot resolve the pro- nouns based on only gender or plurality informa- tion. Recently, Rahman and Ng (2012) gathered a dataset containing 1886 sentences of such challeng- ing pronoun resolution problems (referred to later as the Winograd dataset, following Winograd (1972) and Levesque et al. (2011)). As an indication to the difficulty of these instances, we note that a state-of- the-art coreference resolution system (Chang et al., 2013) achieves precision of 53.26% on it. A special purpose classifier (Rahman and Ng, 2012) trained on this data set achieves 73.05%. The key contribu- tion of this paper is a general purpose, state-of-the- art coreference approach which, at the same time, achieves precision of 76.76% on these hard cases. Addressing these hard coreference problems re- quires significant amounts of background knowl- edge, along with an inference paradigm that can make use of it in supporting the coreference deci- sion. Specifically, in Ex.1 one needs to know that “a limb bends” is more likely than “a bird bends”. In Ex.2 one needs to know that the …

Content truncated to 500 words