Restatement and Question Generation for Counsellor Chatbot

John Lee, Baikun Liang, Haley Fong


Abstract
Amidst rising mental health needs in society, virtual agents are increasingly deployed in counselling. In order to give pertinent advice, counsellors must first gain an understanding of the issues at hand by eliciting sharing from the counsellee. It is thus important for the counsellor chatbot to encourage the user to open up and talk. One way to sustain the conversation flow is to acknowledge the counsellee’s key points by restating them, or probing them further with questions. This paper applies models from two closely related NLP tasks — summarization and question generation — to restatement and question generation in the counselling context. We conducted experiments on a manually annotated dataset of Cantonese post-reply pairs on topics related to loneliness, academic anxiety and test anxiety. We obtained the best performance in both restatement and question generation by fine-tuning BertSum, a state-of-the-art summarization model, with the in-domain manual dataset augmented with a large-scale, automatically mined open-domain dataset.
Anthology ID:
2021.nlp4posimpact-1.1
Volume:
Proceedings of the 1st Workshop on NLP for Positive Impact
Month:
August
Year:
2021
Address:
Online
Editors:
Anjalie Field, Shrimai Prabhumoye, Maarten Sap, Zhijing Jin, Jieyu Zhao, Chris Brockett
Venue:
NLP4PI
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1–7
Language:
URL:
https://aclanthology.org/2021.nlp4posimpact-1.1
DOI:
10.18653/v1/2021.nlp4posimpact-1.1
Bibkey:
Cite (ACL):
John Lee, Baikun Liang, and Haley Fong. 2021. Restatement and Question Generation for Counsellor Chatbot. In Proceedings of the 1st Workshop on NLP for Positive Impact, pages 1–7, Online. Association for Computational Linguistics.
Cite (Informal):
Restatement and Question Generation for Counsellor Chatbot (Lee et al., NLP4PI 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.nlp4posimpact-1.1.pdf