Neural Response Generation with Meta-words

Can Xu, Wei Wu, Chongyang Tao, Huang Hu, Matt Schuerman, Ying Wang


Abstract
We present open domain dialogue generation with meta-words. A meta-word is a structured record that describes attributes of a response, and thus allows us to explicitly model the one-to-many relationship within open domain dialogues and perform response generation in an explainable and controllable manner. To incorporate meta-words into generation, we propose a novel goal-tracking memory network that formalizes meta-word expression as a goal in response generation and manages the generation process to achieve the goal with a state memory panel and a state controller. Experimental results from both automatic evaluation and human judgment on two large-scale data sets indicate that our model can significantly outperform state-of-the-art generation models in terms of response relevance, response diversity, and accuracy of meta-word expression.
Anthology ID:
P19-1538
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5416–5426
Language:
URL:
https://www.aclweb.org/anthology/P19-1538
DOI:
10.18653/v1/P19-1538
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/P19-1538.pdf