| 摘要: |
| 基于树核函数,提出了从使用中心理论、集成竞争者信息和融入语义角色相关信息这3 个方面对结构化句法树进行动态扩展来提升中英文代词消解的性能.首先探索了3 种基本结构化句法树捕获方案,并使用SVMLight 中提供的卷积树核函数直接进行基于结构化句法树的相似度计算,从而完成指代消解任务;其次,在分析3 种结构化句法树捕获方案的基础上,从中心理论、竞争者信息和语义角色相关信息等几方面对捕获的结构化句法树进行了扩展;最后,通过ACE 2004 NWIRE 英文语料和ACE 2005 NWIRE 中文语料上的实验,说明了这些扩展能够提升代词消解的性能. |
| 关键词: 代词消解 结构化句法树 树核函数 |
| DOI：10.3724/SP.J.1001.2012.04044 |
| 分类号: |
| 基金项目:国家自然科学基金(90920004, 61003153); 国家高技术研究发展计划(863)(2012AA011102); 国家教育部博士点基金(200802850006) |
|
| Pronoun Resolution in English and Chinese Languages Based on Tree Kernel |
|
KONG Fang1,2, ZHOU Guo-Dong1,2
|
|
1.Natural Language Processing Laboratory, School of Computer Science and Technology, Soochow University, Suzhou 215006, China;2.Key Laboratory of Computer Information Processing Technology of Jiangsu Province, Suzhou 215006, China
|
| Abstract: |
| This paper proposes a tree kernel method to anaphora resolution of pronouns in both English and Chinese. First, several basic structured tree spans are proposed according to linguistic intuition. The similarity between two structured objects is computed directly using SVMLight. Then, a dynamic-expansion scheme is proposed to automatically determine a proper tree span for pronoun resolution by the centering theory, antecedent competitor-related information, and semantic role-related information. Evaluation on both the ACE 2004 English NWIRE corpus and the ACE 2005 Chinese NWIRE corpus justified the effectiveness of this method. |
| Key words: pronoun resolution structured parse tree tree kernel |
