Abstract

Textual entailment (TE) is a relation that holds between two pieces of text where one reading the first piece can conclude that the second is most likely true. This paper proposes new model based on deep learning approach to recognize textual entailment. The deep learning approach is based on syntactic structure [Holder- Relation - Target] [1] which contains all lexical, syntactic and semantic information about the input text. The proposed model constructs deep leaning neural networks, which aims at building deep and complex encoder to transform a sentence into encoded vectors. The experimental results demonstrate that proposed technique is effective to solve the problem of textual entailment recognition

References

• Mohamed H. Haggag, Hala Abd Al-Galel, Ahmed M. Ahmed, Semantic Roles Labeling Based on Link Parser, The First International Conference for Computing &Informatics, icci 2012 .
• I.Androutsopoulos , P. Malakasiotis , “A Survey of Paraphrasing and Textual Entailment Methods”, Journal of Artificial Intelligence Research 38 (2010) 135-187 , Submitted 12/09; published 05/10.
• R. Adams. "Textual entailment through extended lexical overlap”. In Proceedings of the Second PASCAL Challenges Workshop on Recognising Textual Entailment, pages 128{133, Venice, Italy, April 2006.
• Chu-Carroll, J, and R. Carpenter (1999), Vector-Based Natural Language Call Routing. Journal of Computational Linguistics, 25(30), pp. 361-388, 1999
• J.Bos and K.Markert. “When logical inference helps determining textual entailment” (and when it doesn't). In Proceedings of the Second PASCAL RTE Challenge, Venice, Italy, April 2006.
• Masashi Yoshikawa, Koji Mineshima,” Combining Axiom Injection and Knowledge Base Completion for Efficient Natural Language Inference”, Association for the Advancement of Artificial Intelligence 2018.
• Qian Chen, Xiaodan Zhu, Neural Natural Language Inference Models Enhanced with External Knowledge, Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Long Papers), pages 2406–2417 Melbourne, Australia, July 15 - 20, 2018
• Chaitanya Shivade_ Preethi Raghavany and Siddharth Patwardhan, Addressing Limited Data for Textual Entailment Across Domains, internship at IBM 2016
• Richard Socher, Alex Perelygin, Jean Y. Wu, Jason Chuang, Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank, Rukmani Ravisundaram and Tayyab Tariq 2013
• Chen Lyu, Yanan Lu, Donghong, Deep Learning for Textual Entailment Recognition, 2015 IEEE 27th International Conference on Tools with Artificial Intelligence.
• Daniel D.Sleator and Davy Temperley , Parsing English Sentence using Link Grammar 2003
• Jorge, G., and Eduardo, M., 2008. “Web-Based Measure of Semantic Relatedness”, 9th international conference on Web Information Systems Engineering, Springer-Verlag Berlin, pp. 136-150.
• Li Y., Bandar Z.A., and McLean D. 2003. An Approach for Measuring Semantic Similarity between Words Using Multiple Information Sources. IEEE Trans. on Knowledge and Data Engineering, 15(4), 871-882.
• R. Bar-Haim, J. Berant, and I. Dagan. “A compact forest for scalable inference over entailment and paraphrase rules”. In Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 3, pages 1056{1065, Singapore, August 2009. Association for Computational Linguistics.
• M. Sammons, V.G.V. Vydiswaran, T. Vieira, N. Johri, M.W. Chang, D. Goldwasser, V. Srikumar, G. Kundu, Y. Tu, K. Small, et al. Relation “alignment for textual entailment recognition”. In Proceedings of the 2009 Text Analysis Conference (TAC'09), Gaithersburg, Maryland, USA, November 2009.
• Elisabeth Lien , Milen Kouylekov , UIO-Lien: Entailment Recognition using Minimal Recursion Semantics , Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014), pages 699–703, Dublin, Ireland, August 23-24, 2014.
• Julio Javier Castillo , A Machine Learning Approach for Recognizing Textual Entailment in Spanish , Proceedings of the NAACL HLT 2010 Young Investigators Workshop on Computational Approaches to Languages of the Americas, pages 62–67, Los Angeles, California, June 2010. c 2010 Association for Computational Linguistics .
• Callison-Burch, C., Osborne, M., and Koehn, P. (2006). Re-evaluation the role of bleu in machine translation research.
• MacCartney, B. (June, 2009). Natural Language Inference, Ph.D. thesis. Stanford University.
• Prodromos Malakasiotis, PARAPHRASE AND TEXTUAL ENTAILMENT RECOGNITION AND GENERATION , Ph.D. thesis, ATHENS UNIVERSITY OF ECONOMICS AND BUSINESS.
• Zuzana Nevˇeˇrilová , Paraphrase and Textual Entailment Generation in Czech , , Ph.D. thesis , Masaryk University _ Brno _ 2014.
• R. Adams. Textual entailment through extended lexical overlap. In Proceedings of the Second PASCAL Challenges Workshop on Recognising Textual Entailment, pages 128{133, Venice, Italy, April 2006.