DEEPCOPY: Grounded response generation with hierarchical pointer networks

Semih Yavuz, Abhinav Rastogi, Guan Lin Chao, Dilek Hakkani-Tür

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Recent advances in neural sequence-to-sequence models have led to promising results for several language generation-based tasks, including dialogue response generation, summarization, and machine translation. However, these models are known to have several problems, especially in the context of chit-chat based dialogue systems: they tend to generate short and dull responses that are often too generic. Furthermore, these models do not ground conversational responses on knowledge and facts, resulting in turns that are not accurate, informative and engaging for the users. In this paper, we propose and experiment with a series of response generation models that aim to serve in the general scenario where in addition to the dialogue context, relevant unstructured external knowledge in the form of text is also assumed to be available for models to harness. Our proposed approach extends pointer-generator networks (See et al., 2017) by allowing the decoder to hierarchically attend and copy from external knowledge in addition to the dialogue context. We empirically show the effectiveness of the proposed model compared to several baselines including (Ghazvininejad et al., 2018; Zhang et al., 2018) through both automatic evaluation metrics and human evaluation on CONVAI2 dataset.

Original languageEnglish (US)
Title of host publicationSIGDIAL 2019 - 20th Annual Meeting of the Special Interest Group Discourse Dialogue - Proceedings of the Conference
PublisherAssociation for Computational Linguistics (ACL)
Pages122-132
Number of pages11
ISBN (Electronic)9781950737611
StatePublished - 2019
Externally publishedYes
Event20th Annual Meeting of the Special Interest Group on Discourse and Dialogue, SIGDIAL 2019 - Stockholm, Sweden
Duration: Sep 11 2019Sep 13 2019

Publication series

NameSIGDIAL 2019 - 20th Annual Meeting of the Special Interest Group Discourse Dialogue - Proceedings of the Conference

Conference

Conference20th Annual Meeting of the Special Interest Group on Discourse and Dialogue, SIGDIAL 2019
Country/TerritorySweden
CityStockholm
Period9/11/199/13/19

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Human-Computer Interaction
  • Modeling and Simulation

Fingerprint

Dive into the research topics of 'DEEPCOPY: Grounded response generation with hierarchical pointer networks'. Together they form a unique fingerprint.

Cite this