A Static and Dynamic Attention Framework for Multi Turn Dialogue Generation
ACM Transactions on Information Systems · 31.01.2023 · 41 (1) · 1-30
DOI: 10.1145/3522763 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Information Systems, online erschienen am 09.01.2023. Verfasst von Weinan Zhang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 48 Literaturangaben. Gefördert von: Science and Technology Innovation 2030 Major Project of China, National Natural Science Foundation of China.
Abstract (Originalsprache)
Recently, research on open domain dialogue systems have attracted extensive interests of academic and industrial researchers. The goal of an open domain dialogue system is to imitate humans in conversations. Previous works on single turn conversation generation have greatly promoted the research of open domain dialogue systems. However, understanding multiple single turn conversations is not equal to the understanding of multi turn dialogue due to the coherent and context dependent properties of human dialogue. Therefore, in open domain multi turn dialogue generation, it is essential to modeling the contextual semantics of the dialogue history rather than only according to the last utterance. Previous research had verified the effectiveness of the hierarchical recurrent encoder-decoder framework on open domain multi turn dialogue generation. However, using an RNN-based model to hierarchically encoding the utterances to obtain the representation of dialogue history still face the problem of a vanishing gradient. To address this issue, in this article, we proposed a static and dynamic attention-based approach to model the dialogue history and then generate open domain multi turn dialogue responses. Experimental results on the Ubuntu and Opensubtitles datasets verify the effectiveness of the proposed static and dynamic attention-based approach on automatic and human evaluation metrics in various experimental settings. Meanwhile, we also empirically verify the performance of combining the static and dynamic attentions on open domain multi turn dialogue generation.
Förderung
- Science and Technology Innovation 2030 Major Project of China
- National Natural Science Foundation of China
Zitieren
APA
Zhang, W., Cui, Y., Zhang, K., Wang, Y., Zhu, Q., Li, L., & Liu, T. (2023). A Static and Dynamic Attention Framework for Multi Turn Dialogue Generation. ACM Transactions on Information Systems, 41(1), 1-30. https://doi.org/10.1145/3522763
Vancouver
Zhang W, Cui Y, Zhang K, Wang Y, Zhu Q, Li L, et al. A Static and Dynamic Attention Framework for Multi Turn Dialogue Generation. ACM Transactions on Information Systems. 2023;41(1):1-30. doi:10.1145/3522763
BibTeX
@article{Zhang2023,
author = {Zhang, Weinan and Cui, Yiming and Zhang, Kaiyan and Wang, Yifa and Zhu, Qingfu and Li, Lingzhi and Liu, Ting},
title = {A Static and Dynamic Attention Framework for Multi Turn Dialogue Generation},
journal = {ACM Transactions on Information Systems},
year = {2023},
volume = {41},
number = {1},
pages = {1--30},
doi = {10.1145/3522763}
}
EUVIMED