Context-Aware Dual-Attention Network for Natural Language Inference

  • Kun Zhang
  • Guangyi Lv
  • Enhong ChenEmail author
  • Le Wu
  • Qi Liu
  • C. L. Philip Chen
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11441)


Natural Language Inference (NLI) is a fundamental task in natural language understanding. In spite of the importance of existing research on NLI, the problem of how to exploit the contexts of sentences for more precisely capturing the inference relations (i.e. by addressing the issues such as polysemy and ambiguity) is still much open. In this paper, we introduce the corresponding image into inference process. Along this line, we design a novel Context-Aware Dual-Attention Network (CADAN) for tackling NLI task. To be specific, we first utilize the corresponding images as the Image Attention to construct an enriched representation for sentences. Then, we use the enriched representation as the Sentence Attention to analyze the inference relations from detailed perspectives. Finally, a sentence matching method is designed to determine the inference relation in sentence pairs. Experimental results on large-scale NLI corpora and real-world NLI alike corpus demonstrate the superior effectiveness of our CADAN model.



This research was partially supported by grants from the National Key Research and Development Program of China (No. 2016YFB1000904) and the National Natural Science Foundation of China (Grants No. 61727809, U1605251, 61572540, and 61751202).


  1. 1.
    Altmann, G., Steedman, M.: Interaction with context during human sentence processing. Cognition 30(3), 191–238 (1988)CrossRefGoogle Scholar
  2. 2.
    Bowman, S.R., Angeli, G., Potts, C., Manning, C.D.: A large annotated corpus for learning natural language inference. In: EMNLP (2015)Google Scholar
  3. 3.
    Chen, Q., Zhu, X., Ling, Z.H., Wei, S., Jiang, H., Inkpen, D.: Recurrent neural network-based sentence encoder with gated attention for natural language inference. arXiv preprint arXiv:1708.01353 (2017)
  4. 4.
    Chen, Q., Zhu, X., Ling, Z., Wei, S., Jiang, H., Inkpen, D.: Enhanced LSTM for natural language inference. In: ACL. ACL, Vancouver, July 2017Google Scholar
  5. 5.
    Cheng, J., Dong, L., Lapata, M.: Long short-term memory-networks for machine reading. In: EMNLP (2016)Google Scholar
  6. 6.
    Cho, K., Courville, A.C., Bengio, Y.: Describing multimedia content using attention-based encoder-decoder networks. IEEE Trans. Multimed. 17, 1875–1886 (2015)CrossRefGoogle Scholar
  7. 7.
    Chung, J., Gulcehre, C., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. CoRR abs/1412.3555 (2014)Google Scholar
  8. 8.
    Gururangan, S., Swayamdipta, S., Levy, O., Schwartz, R., Bowman, S.R., Smith, N.A.: Annotation artifacts in natural language inference data. arXiv preprint arXiv:1803.02324 (2018)
  9. 9.
    Huang, Z., et al.: Question difficulty prediction for READING problems in standard tests. In: AAAI (2017)Google Scholar
  10. 10.
    Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: CVPR, pp. 3128–3137 (2015)Google Scholar
  11. 11.
    Khot, T., Sabharwal, A., Clark, P.: SciTail: a textual entailment dataset from science question answering. In: AAAI (2018)Google Scholar
  12. 12.
    Kingma, D.P., Welling, M.: Auto-encoding variational bayes. CoRR abs/1312.6114 (2013)Google Scholar
  13. 13.
    Klein, B., Lev, G., Sadeh, G., Wolf, L.: Associating neural word embeddings with deep image representations using Fisher Vectors. In: CVPR, pp. 4437–4446 (2015)Google Scholar
  14. 14.
    Kun, Z., Guangyi, L., Le, W., Enhong, C., Qi, L., Han, W.: Image-enhanced multi-level sentence representation net for natural language inference. In: ICDM (2018)Google Scholar
  15. 15.
    Lai, A., Bisk, Y., Hockenmaier, J.: Natural language inference from multiple premises. In: IJCNLP (2017)Google Scholar
  16. 16.
    Liu, Y., Sun, C., Lin, L., Wang, X.: Learning natural language inference using bidirectional LSTM model and inner-attention. CoRR abs/1605.09090 (2016)Google Scholar
  17. 17.
    Lv, G., Xu, T., Chen, E., Liu, Q., Zheng, Y.: Reading the videos: temporal labeling for crowdsourced time-sync videos based on semantic embedding. In: AAAI (2016)Google Scholar
  18. 18.
    Ma, L., Lu, Z., Shang, L., Li, H.: Multimodal convolutional neural networks for matching image and sentence. In: ICCV, pp. 2623–2631 (2015)Google Scholar
  19. 19.
    MacCartney, B.: Natural Language Inference. Stanford University, Stanford (2009)Google Scholar
  20. 20.
    Mao, J., Xu, W., Yang, Y., Wang, J., Yuille, A.L.: Deep captioning with multimodal recurrent neural networks (m-RNN). CoRR abs/1412.6632 (2014)Google Scholar
  21. 21.
    Mou, L., et al.: Natural language inference by tree-based convolution and heuristic matching. In: ACL (2016)Google Scholar
  22. 22.
    Munkhdalai, T., Yu, H.: Neural tree indexers for text understanding. CoRR abs/1607.04492 (2016)Google Scholar
  23. 23.
    Orr, G.B., Müller, K.R.: Neural Networks: Tricks of the Trade. Springer, Heidelberg (2003)Google Scholar
  24. 24.
    Pan, Y., Mei, T., Yao, T., Li, H., Rui, Y.: Jointly modeling embedding and translation to bridge video and language. In: CVPR, pp. 4594–4602 (2016)Google Scholar
  25. 25.
    Parikh, A.P., Täckström, O., Das, D., Uszkoreit, J.: A decomposable attention model for natural language inference. In: EMNLP (2016)Google Scholar
  26. 26.
    Pennington, J., Socher, R., Manning, C.: GloVe: global vectors for word representation. In: EMNLP, pp. 1532–1543 (2014)Google Scholar
  27. 27.
    Clark, P., et al.: Combining retrieval, statistics, and inference to answer elementary science questions. In: AAAI (2016)Google Scholar
  28. 28.
    Ren, M., Kiros, R., Zemel, R.S.: Exploring models and data for image question answering. In: NIPS (2015)Google Scholar
  29. 29.
    Rocktäschel, T., Grefenstette, E., Hermann, K.M., Kociský, T., Blunsom, P.: Reasoning about entailment with neural attention. CoRR abs/1509.06664 (2015)Google Scholar
  30. 30.
    Ruder, S.: An overview of gradient descent optimization algorithms. CoRR abs/1609.04747 (2016)Google Scholar
  31. 31.
    Rush, A.M., Chopra, S., Weston, J.: A neural attention model for abstractive sentence summarization. In: EMNLP (2015)Google Scholar
  32. 32.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR abs/1409.1556 (2014)Google Scholar
  33. 33.
    Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: CVPR, pp. 3156–3164 (2015)Google Scholar
  34. 34.
    Wang, S., Jiang, J.: Learning natural language inference with LSTM. In: HLT-NAACL (2016)Google Scholar
  35. 35.
    Weeds, J., Clarke, D., Reffin, J., Weir, D.J., Keller, B.: Learning to distinguish hypernyms and co-hyponyms. In: COLING, pp. 2249–2259 (2014)Google Scholar
  36. 36.
    Williams, A., Nangia, N., Bowman, S.R.: A broad-coverage challenge corpus for sentence understanding through inference. CoRR abs/1704.05426 (2017)Google Scholar
  37. 37.
    Yin, Y., et al.: Transcribing content from structural images with spotlight mechanism. In: KDD (2018)Google Scholar
  38. 38.
    Zhang, K., Chen, E., Liu, Q., Liu, C., Lv, G.: A context-enriched neural network method for recognizing lexical entailment. In: AAAI (2017)Google Scholar
  39. 39.
    Zheng, X., Feng, J., Chen, Y., Peng, H., Zhang, W.: Learning context-specific word/character embeddings. In: AAAI (2017)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Kun Zhang
    • 1
  • Guangyi Lv
    • 1
  • Enhong Chen
    • 1
    Email author
  • Le Wu
    • 2
  • Qi Liu
    • 1
  • C. L. Philip Chen
    • 3
  1. 1.Anhui Province Key Laboratory of Big Data Analysis and Application, School of Computer Science and TechnologyUniversity of Science and Technology of ChinaHefeiChina
  2. 2.Hefei University of TechnologyHefeiChina
  3. 3.University of MacauMacauChina

Personalised recommendations