The generation of textual entailment with NLML in an intelligent dialogue system for language learning CSIEC

This paper introduces the generation of textual entailment within the project CSIEC (computer simulation in educational communication), an interactive Web-based human-computer dialogue system with natural language for English instruction. The generation of textual entailment (GTE) is critical to the further improvement of CSIEC project and other natural language generation program. Up to now we have found few literatures on the general algorithm for GTE. Simulating the process that a human being learns English as a foreign language, we explore our naive approach to tackle the GTE problem and its algorithm within the framework of CSIEC, i.e. rule annotation in NLML, pattern recognition and entailment transformation. The time and space complexity of our algorithm is tested with some entailment examples. An interactive command line textual entailment editor is created to generalize an entailment rule from a case pair of text and entailment. The test version of this innovative GTE approach can be accessed in the CSIEC website. Further works include the rules annotation based on the English textbooks and a GUI interface for normal users to edit the entailment rules.

[1]  Satoshi Sekine,et al.  Automatic Paraphrase Discovery based on Context and Keywords between NE Pairs , 2005, IJCNLP.

[2]  Jiyou Jia,et al.  CSIEC (computer simulator in educational communication): a virtual context-adaptive chatting partner for foreign language learners , 2004, IEEE International Conference on Advanced Learning Technologies, 2004. Proceedings..

[3]  Weichao Chen,et al.  Script-Based Design for Human-Computer Dialog in Given Scenarios for English Learners , 2008, 2008 Eighth IEEE International Conference on Advanced Learning Technologies.

[4]  Viktor Pekar.  Acquisition of Verb Entailment from Text , 2006, HLT-NAACL.

[5]  Mark Stefik,et al.  Introduction to knowledge systems , 1995 .

[6]  Dan Roth,et al.  Knowledge Representation for Semantic Entailment and Question-Answering , 1995 .

[7]  Terry Winograd,et al.  Understanding natural language , 1974 .

[8]  Xiping Song.  A framework for understanding the integration of design methodologies , 1995, SOEN.

[9]  Ido Dagan,et al.  The Distributional Inclusion Hypotheses and Lexical Entailment , 2005, ACL.

[10]  Christopher D. Manning,et al.  Learning to recognize features of valid textual entailments , 2006, NAACL.

[11]  Roy Bar-Haim,et al.  The Second PASCAL Recognising Textual Entailment Challenge , 2006 .

[12]  Christiane Fellbaum,et al.  Book Reviews: WordNet: An Electronic Lexical Database , 1999, CL.

[13]  Ido Dagan,et al.  Feature Vector Quality and Distributional Similarity , 2004, COLING.

[14]  Ido Dagan,et al.  Investigating a Generic Paraphrase-Based Approach for Relation Extraction , 2006, EACL.

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

[16]  Udo Hahn,et al.  Towards Text Knowledge Engineering , 1998, AAAI/IAAI.

[17]  Regina Barzilay,et al.  Learning to Paraphrase: An Unsupervised Approach Using Multiple-Sequence Alignment , 2003, NAACL.

[18]  Satoshi Sekine,et al.  Automatic paraphrase acquisition from news articles , 2002 .

[19]  Ido Dagan,et al.  The Third PASCAL Recognizing Textual Entailment Challenge , 2007, ACL-PASCAL@ACL.

[20]  Johan Bos,et al.  Recognising Textual Entailment with Logical Inference , 2005, HLT.

[21]  Patrick Pantel,et al.  Discovery of inference rules for question-answering , 2001, Natural Language Engineering.

[22]  Roy Bar-Haim,et al.  Definition and Analysis of Intermediate Entailment Levels , 2005, EMSEE@ACL.

[23]  Arthur C. Graesser,et al.  Lexico-syntactic subsumption for textual entailment , 2007 .

[24]  Roger C. Schank,et al.  An Integrated Understander , 1980, Am. J. Comput. Linguistics.

[25]  Dekang Lin,et al.  Dependency-Based Evaluation of Minipar , 2003 .

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

[27]  Jiyou Jia,et al.  NLML - a Markup Language to Describe the Unlimited English Grammar , 2004, ArXiv.

[28]  Roger C. Schank,et al.  Scripts, plans, goals and understanding: an inquiry into human knowledge structures , 1978 .

[29]  Ralph Grishman,et al.  Discovering Relations among Named Entities from Large Corpora , 2004, ACL.

[30]  Cornelis H. A. Koster.  Affix Grammars for Natural Languages , 1991, Attribute Grammars, Applications and Systems.

[31]  Jiyou Jia.  NLOMJ - Natural Language Object Modal in Java , 2004, Intelligent Information Processing.