Knowledge-aware Pronoun Coreference Resolution

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 867–876 Florence, Italy, July 28 - August 2, 2019. c⃝2019 Association for Computational Linguistics 867 Knowledge-aware Pronoun Coreference Resolution Hongming Zhang♣∗, Yan Song♠, Yangqiu Song♣, and Dong Yu♠ ♣Department of CSE, The Hong Kong University of Science and Technology ♠Tencent AI Lab hzhangal@cse.ust.hk, clksong@gmail.com, yqsong@cse.ust.hk, dyu@tencent.com Abstract Resolving pronoun coreference requires knowledge support, especially for particular domains (e.g., medicine). In this paper, we explore how to leverage different types of knowledge to better resolve pronoun coreference with a neural model. To ensure the generalization ability of our model, we directly incorporate knowledge in the format of triplets, which is the most common format of modern knowledge graphs, instead of encoding it with features or rules as that in conventional approaches. Moreover, since not all knowledge is helpful in certain contexts, to selectively use them, we propose a knowledge attention module, which learns to select and use informative knowledge based on contexts, to enhance our model. Experimental results on two datasets from different domains prove the validity and effectiveness of our model, where it outperforms state-of-the-art baselines by a large margin. Moreover, since our model learns to use external knowledge rather than only fitting the training data, it also demonstrates superior performance to baselines in the cross-domain setting. 1 Introduction Being an important human language phenomenon, coreference brings simplicity for human languages while introducing a huge challenge for machines to process, especially for pronouns, which are hard to be interpreted owing to their weak semantic meanings (Ehrlich, 1981). As one challenging yet vital subtask of the general coreference resolution, pronoun coreference resolution (Hobbs, 1978) is to find the correct reference for a given pronominal anaphor in the context and has showed its impor- tance in many natural language processing (NLP) ∗This work was partially done during the internship of the first author in Tencent AI Lab. Example A Example B Sentence The apple on the table looks great and I want to eat it. Yesterday, the patient took the CT scan in the hospital and it showed that she had recovered. Pronoun it it Answer The apple the CT scan Knowledge We can eat ap- ples but we can- not eat a table. A ‘test’ shows results to patients; ‘the CT scan’ is a medical test. Table 1: Demonstration of two pronoun corefer- ence examples, which require complex knowledge (ex- plained in the table) to resolve. Pronouns and their cor- responding mentions are marked in bold red and under- line blue fonts, respectively. tasks, such as machine translation (Mitkov et al., 1995), dialog systems (Strube and M¨uller, 2003), information extraction (Edens et al., 2003), and summarization (Steinberger et al., 2007), etc. In general, to resolve pronoun coreferences, one needs intensive knowledge support. As shown in Table 1, answering the first question requires the knowledge on which object can be eaten (ap- ple v.s. table), while the second question re- quires the knowledge that the CT scan is a …

Content truncated to 500 words