A Feature-Enriched Tree Kernel for Relation Extraction
Le Sun, Xianpei Han · 2014
Tree kernel is an effective technique for rela-tion extraction. However, the traditional syn-tactic tree representation is often too coarse or ambiguous to accurately capture the semantic relation information between two entities. In this paper, we propose a new tree kernel, called feature-enriched tree kernel (FTK), which can enhance the traditional tree kernel by: 1) refining the syntactic tree representation by annotating each tree node with a set of dis-criminant features; and 2) proposing a new tree kernel which can better measure the syn-tactic tree similarity by taking all features into consideration. Experimental results show that our method can achieve a 5.4 % F-measure im-provement over the traditional convolution tree kernel. 1