中央研究院 資訊科學研究所

Textual Entailment (TE) is a critical issue in natural language processing (NLP). I will report how our hybrid approach system works in NTCIR-11 RITE-VAL task. We attended both Fact Validation (FV) and System Validation (SV) subtasks for Chinese. In the SV subtask, we also attended both binary classification (BC) and multi-classification (MC). For the SV BC subtask, our system detects eleven special cases for the input pairs, and uses twelve SVM classifiers to do classification. The results then are integrated as the system report. For the SV MC subtask, we also train four SVM classifiers for the Bidirectional, Forward, Independence, and Contradiction. The results are integrated by rules. For the FV subtask, our system searches the Wikipedia to find the top one T1 and decides the entailment relation to T2 by rules.

Prof. Shih-Hung Wu is an assistant professor at Department of Computer Science and Information Engineering, Chaoyang University of Technology, currently working on natural language processing related researches. He was a Post-Doctoral Fellow at Institute of Information Science, Academia Sinica in Taiwan. He received the B.S. degree from the National Taiwan University, the Master degree and the Ph.D. degree in Computer Science from the National Tsing Hua University, Taiwan, on 1993 and 1999 respectively. His research interests cover information retrieval, natural language processing, learning technology, and robotics.