A divide-and-conquer strategy for semantic dependency parsing
Qiaoli Zhou, Zhang Ling, Fei Liu, Dongfeng Cai, Guangping Zhang · Joint Conference on Lexical and Computational Semantics · 2012
We describe our SemEval2012 shared Task 5 system in this paper. The system includes three cascaded components: the tagging semantic role phrase, the identification of semantic role phrase, phrase and frame semantic dependency parsing. In this paper, semantic role phrase is tagged automatically based on rules, and takes Conditional Random Fields (CRFs) as the statistical identification model of semantic role phrase. A projective graph-based parser is used as our semantic dependency parser. Finally, we gain Labeled Attachment Score (LAS) of 61.84%, which ranked the first position. At present, we gain the LAS of 62.08%, which is 0.24% higher than that ranked the first position in the task 5.