Infusing Knowledge into the Textual Entailment Task Using Graph Convolutional Networks


  • Pavan Kapanipathi IBM Research
  • Veronika Thost IBM Research
  • Siva Sankalp Patel IBM Research
  • Spencer Whitehead University of Illinois at Urbana-Champaign
  • Ibrahim Abdelaziz IBM Research
  • Avinash Balakrishnan IBM Research
  • Maria Chang IBM Research
  • Kshitij Fadnis IBM Research
  • Chulaka Gunasekara IBM Research
  • Bassem Makni IBM Research
  • Nicholas Mattei Tulane University
  • Kartik Talamadupula IBM Research
  • Achille Fokoue IBM Research



Textual entailment is a fundamental task in natural language processing. Most approaches for solving this problem use only the textual content present in training data. A few approaches have shown that information from external knowledge sources like knowledge graphs (KGs) can add value, in addition to the textual content, by providing background knowledge that may be critical for a task. However, the proposed models do not fully exploit the information in the usually large and noisy KGs, and it is not clear how it can be effectively encoded to be useful for entailment. We present an approach that complements text-based entailment models with information from KGs by (1) using Personalized PageRank to generate contextual subgraphs with reduced noise and (2) encoding these subgraphs using graph convolutional networks to capture the structural and semantic information in KGs. We evaluate our approach on multiple textual entailment datasets and show that the use of external knowledge helps the model to be robust and improves prediction accuracy. This is particularly evident in the challenging BreakingNLI dataset, where we see an absolute improvement of 5-20% over multiple text-based entailment models.




How to Cite

Kapanipathi, P., Thost, V., Sankalp Patel, S., Whitehead, S., Abdelaziz, I., Balakrishnan, A., Chang, M., Fadnis, K., Gunasekara, C., Makni, B., Mattei, N., Talamadupula, K., & Fokoue, A. (2020). Infusing Knowledge into the Textual Entailment Task Using Graph Convolutional Networks. Proceedings of the AAAI Conference on Artificial Intelligence, 34(05), 8074-8081.



AAAI Technical Track: Natural Language Processing