基于中心理论的指代消解研究

Coreference Resolution Based on Center Theory

系统分析了在中心理论指导下语义角色在指代消解中的应用。首先使用性能良好的语义角色标注工具AS-SERT自动进行语义角色的识别,然后将识别出的语义角色信息与代词类别特征相组合进行指代消解。以中心理论为基础来表示、使用语义角色信息。从ACE 2003语料库上的实验结果可以看到,引入语义角色后,与基准系统相比,系统的F值提高了2.2%。特别是代词的指代消解,从实验结果可以看到,性能得到了大大提升。

We systematically explored the use of semantic roles in coreference resolution. Here,the semantic roles were automatically determined using a state-of-the-art SRL system, ASSERT, and integrated into the resolution by combining them with pronoun categories. In particular, this paper employed the semantic roles information based on center theory. Experimental results on the ACE 2003 corpus show that our method can outperform the baseline system by 2. 2% in Fmeasure. Especially for pronoun, the experiments show that the refine system using semantic roles information can significantly boost the performance of the baseline for pronoun resolution.