LTI's Textual Entailment Recognizer System at NTCIR-9 RITE

paper describes the LTI's system participated in NTCIR-9 RITE. The system is based on multiple linguistically-motivated features and an adaptable framework for different datasets. The formal run scores are 54.6% (accuracy in BC), 66.7% (accuracy in Entrance Exam), and 29.8% (MRR in RITE4QA) which outperformed strong baselines, and are relatively good among participants. We also describe in-house experimental results (e.g. ablation study for measuring feature contribution).

[1]  Ido Dagan,et al.  Web Based Probabilistic Textual Entailment , 2005 .

[2]  Timothy Baldwin,et al.  Detecting Entailment Using an Extended Implementation of the Basic Elements Overlap Metric , 2006 .

[3]  Yuji Matsumoto,et al.  Applying Conditional Random Fields to Japanese Morphological Analysis , 2004, EMNLP.

[4]  Jun-ichi Fukumoto,et al.  Automated Summarization Evaluation with Basic Elements. , 2006, LREC.

[5]  Hitoshi Isahara,et al.  Development of the Japanese WordNet , 2008, LREC.

[6]  George A. Miller,et al.  WordNet: A Lexical Database for English , 1995, HLT.

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

[8]  Alexander Yates,et al.  Types of Common-Sense Knowledge Needed for Recognizing Textual Entailment , 2011, ACL.

[9]  Weiwei Guo,et al.  Committed Belief Annotation and Tagging , 2009, Linguistic Annotation Workshop.

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

[11]  Adam L. Berger,et al.  A Maximum Entropy Approach to Natural Language Processing , 1996, CL.

[12]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[13]  Jong-Hoon Oh,et al.  Bilingual Co-Training for Monolingual Hyponymy-Relation Acquisition , 2009, ACL.

[14]  Yuji Matsumoto,et al.  Japanese Dependency Analysis using Cascaded Chunking , 2002, CoNLL.

[15]  Jun-ichi Fukumoto,et al.  Question Answering System for Non-factoid Type Questions and Automatic Evaluation based on BE Method , 2007, NTCIR.

[16]  Kentaro Torisawa,et al.  Boosting Precision and Recall of Hyponymy Relation Acquisition from Hierarchical Layouts in Wikipedia , 2008, LREC.

[17]  Chih-Jen Lin,et al.  Probability Estimates for Multi-class Classification by Pairwise Coupling , 2003, J. Mach. Learn. Res..