Generating Textual Entailment Using Residual LSTMs
- 1.5k Downloads
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.
KeywordsGenerating textual entailment Natural language generation Natural language processing Artificial intelligence
This paper was supported by the National Natural Science Foundation of China (Grant No. 61472105, 61472107), The National High Technology Research and Development Program of China (863 Program) (2015AA015407).
- 1.Bowman, S.R., et al.: A large annotated corpus for learning natural language inference. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (EMNLP). Association for Computational Linguistics (2015). doi: 10.18653/v1/d15-1075
- 2.Chen, Q., et al.: Enhancing and Combining Sequential and Tree LSTM for Natural Language Inference (2017). arXiv:160906038 Cs
- 5.He, K., et al.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2016). doi: 10.1109/cvpr.2016.90
- 6.Jia, J.: The generation of textual entailment with NLML in an intelligent dialogue system for language learning CSIEC. In: International Conference on Natural Language Processing and Knowledge Engineering, NLP-KE 2008, pp. 1–8. IEEE (2008). doi: 10.1109/nlpke.2008.4906806
- 7.Kolesnyk, V., et al.: Generating Natural Language Inference Chains (2016). arXiv preprint: arXiv:160601404
- 8.Magnini, B., et al.: The excitement open platform for textual inferences. In: ACL (System Demonstrations), pp. 43–48 (2014). doi: 10.3115/v1/p14-5008
- 10.Papineni, K., et al.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, pp. 311–318. Association for Computational Linguistics (2002). doi: 10.3115/1073083.1073135
- 11.Pennington, J., et al.: Glove: global vectors for word representation. In: EMNLP, pp. 1532–1543 (2014). doi: 10.3115/v1/d14-1162
- 12.Prakash, A., et al.: Neural Paraphrase Generation with Stacked Residual LSTM Networks (2016). arXiv:161003098 Cs
- 13.Toderici, G., et al.: Full Resolution Image Compression with Recurrent Neural Networks (2016). arXiv preprint: arXiv:160805148