Generating Textual Entailment Using Residual LSTMs

• Published in: Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data Vol. 10565; pp. 263 - 272
• Main Authors: Guo, Maosheng, Zhang, Yu, Zhao, Dezhi, Liu, Ting
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2017; Springer International Publishing
• Series: Lecture Notes in Computer Science
• Subjects: Artificial intelligence; Generating textual entailment; Natural language generation; Natural language processing
• ISBN: 3319690043; 9783319690049
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-319-69005-6_22

Generating textual entailment (GTE) is a recently proposed task to study how to infer a sentence from a given premise. Current sequence-to-sequence GTE models are prone to produce invalid sentences when facing with complex enough premises. Moreover, the lack of appropriate evaluation criteria hinders researches on GTE. In this paper, we conjecture that the unpowerful encoder is the major bottleneck in generating more meaningful sequences, and improve this by employing the residual LSTM network. With the extended model, we obtain state-of-the-art results. Furthermore, we propose a novel metric for GTE, namely EBR (Evaluated By Recognizing textual entailment), which could evaluate different GTE approaches in an objective and fair way without human effort while also considering the diversity of inferences. In the end, we point out the limitation of adapting a general sequence-to-sequence framework under GTE settings, with some proposals for future research, hoping to generate more public discussion.