论文信息 - The Description of the NTOU RITE System in NTCIR-9

The Description of the NTOU RITE System in NTCIR-9

textual entailment system determines whether one sentence entails another in common sense. This is the second time of a RITE task in NTCIR projects. Three different subtasks, BC, MC, and RITE4QA, were held this time. We proposed several new features, and tried to construct RITE systems by using binary- or multi-class classifiers. After correcting errors in our submitted runs, our best (unofficial) system in the BC subtask achieves 65.12% in macro F-measure and 66.52% in accuracy. The performance of our MC classifiers is around 44.8% in macro F-measure and 56.64% in accuracy. Our best (unofficial) system in the RITE4QA subtask achieves 32.67% in Top1 accuracy, 41.74% in MRR, and 56% in Top 5 accuracy regarding to the WorseRanking.

Chuan-Jie Lin | Bo-Yu Hsiao

[1] Johan Bos,et al. Textual Entailment at EVALITA 2009 , 2009 .

[2] G. Clark,et al. Reference , 2008 .

[3] M. Felisa Verdejo,et al. Overview of the Answer Validation Exercise 2007 , 2006, CLEF.

[4] Martha Palmer,et al. Verb Semantics and Lexical Selection , 1994, ACL.

[5] M. Felisa Verdejo,et al. Overview of the Answer Validation Exercise 2007 , 2007, CLEF.

[6] Proceedings of the 10th NTCIR Conference on Evaluation of Information Access Technologies, NTCIR-10, National Center of Sciences, Tokyo, Japan, June 18-21, 2013 , 2013, NTCIR.

[7] Elena Lloret,et al. A Text Summarization Approach under the Influence of Textual Entailment , 2016, NLPCS.

[8] Ido Dagan,et al. The Sixth PASCAL Recognizing Textual Entailment Challenge , 2009, TAC.

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

[10] Peter Clark,et al. The Seventh PASCAL Recognizing Textual Entailment Challenge , 2011, TAC.