MovieChats: Chat like Humans in a Closed Domain

Hui Su, Xiaoyu Shen, Zhou Xiao, Zheng Zhang, Ernie Chang, Cheng Zhang, Cheng Niu, Jie Zhou


Abstract
Being able to perform in-depth chat with humans in a closed domain is a precondition before an open-domain chatbot can be ever claimed. In this work, we take a close look at the movie domain and present a large-scale high-quality corpus with fine-grained annotations in hope of pushing the limit of movie-domain chatbots. We propose a unified, readily scalable neural approach which reconciles all subtasks like intent prediction and knowledge retrieval. The model is first pretrained on the huge general-domain data, then finetuned on our corpus. We show this simple neural approach trained on high-quality data is able to outperform commercial systems replying on complex rules. On both the static and interactive tests, we find responses generated by our system exhibits remarkably good engagement and sensibleness close to human-written ones. We further analyze the limits of our work and point out potential directions for future work
Anthology ID:
2020.emnlp-main.535
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6605–6619
Language:
URL:
https://www.aclweb.org/anthology/2020.emnlp-main.535
DOI:
10.18653/v1/2020.emnlp-main.535
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/2020.emnlp-main.535.pdf
Optional supplementary material:
 2020.emnlp-main.535.OptionalSupplementaryMaterial.pdf