TY - GEN
T1 - DEEPCOPY
T2 - 20th Annual Meeting of the Special Interest Group on Discourse and Dialogue, SIGDIAL 2019
AU - Yavuz, Semih
AU - Rastogi, Abhinav
AU - Chao, Guan Lin
AU - Hakkani-Tür, Dilek
N1 - Publisher Copyright:
©2019 Association for Computational Linguistics
PY - 2019
Y1 - 2019
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85084802042&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85084802042&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85084802042
T3 - SIGDIAL 2019 - 20th Annual Meeting of the Special Interest Group Discourse Dialogue - Proceedings of the Conference
SP - 122
EP - 132
BT - SIGDIAL 2019 - 20th Annual Meeting of the Special Interest Group Discourse Dialogue - Proceedings of the Conference
PB - Association for Computational Linguistics (ACL)
Y2 - 11 September 2019 through 13 September 2019
ER -