Filling Conversation Ellipsis for Better Social Dialog Understanding


  • Xiyuan Zhang Zhejiang University
  • Chengxi Li Zhejiang University
  • Dian Yu University of California, Davis
  • Samuel Davidson University of California, Davis
  • Zhou Yu University of California, Davis



The phenomenon of ellipsis is prevalent in social conversations. Ellipsis increases the difficulty of a series of downstream language understanding tasks, such as dialog act prediction and semantic role labeling. We propose to resolve ellipsis through automatic sentence completion to improve language understanding. However, automatic ellipsis completion can result in output which does not accurately reflect user intent. To address this issue, we propose a method which considers both the original utterance that has ellipsis and the automatically completed utterance in dialog act and semantic role labeling tasks. Specifically, we first complete user utterances to resolve ellipsis using an end-to-end pointer network model. We then train a prediction model using both utterances containing ellipsis and our automatically completed utterances. Finally, we combine the prediction results from these two utterances using a selection model that is guided by expert knowledge. Our approach improves dialog act prediction and semantic role labeling by 1.3% and 2.5% in F1 score respectively in social conversations. We also present an open-domain human-machine conversation dataset with manually completed user utterances and annotated semantic role labeling after manual completion.




How to Cite

Zhang, X., Li, C., Yu, D., Davidson, S., & Yu, Z. (2020). Filling Conversation Ellipsis for Better Social Dialog Understanding. Proceedings of the AAAI Conference on Artificial Intelligence, 34(05), 9587-9595.



AAAI Technical Track: Natural Language Processing