论文信息 - Recognizing Text Entailment via Syntactic Tree Matching

Recognizing Text Entailment via Syntactic Tree Matching

paper, we present our approach for Chinese Binary-class (BC) subtask of Recognizing Inference in Text (RITE) task in NTCIR-9 (9). Our system is to judge whether a given sentence can entail another or not. Firstly each sentence is parsed to a syntactic tree in which nodes represent words or phrase, and links represent syntactic relationships between nodes. Then, the entailment between two sentences is recognized by syntactic tree matching. In addition, to compute the similarity between two words or phrases, the external resources (Tongyici Cilin, HowNet 1 , and Hudong Wiki 2 ) are employed. The evaluation results show that our system can reach the accuracy of 87.1% in recognizing pairs with entailment relationship.

Yue Zhang | Dong-Hong Ji | Zhewei Mai

[1] Rajat Raina,et al. Robust Textual Inference Via Learning and Abductive Reasoning , 2005, AAAI.

[2] Sanda M. Harabagiu,et al. COGEX: A Logic Prover for Question Answering , 2003, NAACL.

[3] Shuming Shi,et al. Overview of NTCIR-9 RITE: Recognizing Inference in TExt , 2011, NTCIR.

[4] Kai Wang,et al. A syntactic tree matching approach to finding similar questions in community-based qa services , 2009, SIGIR.

[5] Qun Liu,et al. 基於《知網》的辭彙語義相似度計算 (Word Similarity Computing Based on How-net) [In Chinese] , 2002, ROCLING/IJCLCLP.

[6] Andrew Y. Ng,et al. Robust Textual Inference via Graph Matching , 2005, HLT.

[7] Tian Xia. An Edit Distance Algorithm with Block Swap , 2008, 2008 The 9th International Conference for Young Computer Scientists.

[8] Andrew Hickl,et al. Recognizing Textual Entailment with LCC’s G ROUNDHOG System , 2005 .