Interactive Classification by Asking Informative Questions

Lili Yu, Howard Chen, Sida I. Wang, Tao Lei, Yoav Artzi


Abstract
We study the potential for interaction in natural language classification. We add a limited form of interaction for intent classification, where users provide an initial query using natural language, and the system asks for additional information using binary or multi-choice questions. At each turn, our system decides between asking the most informative question or making the final classification pre-diction. The simplicity of the model allows for bootstrapping of the system without interaction data, instead relying on simple crowd-sourcing tasks. We evaluate our approach on two domains, showing the benefit of interaction and the advantage of learning to balance between asking additional questions and making the final prediction.
Anthology ID:
2020.acl-main.237
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2664–2680
Language:
URL:
https://aclanthology.org/2020.acl-main.237
DOI:
10.18653/v1/2020.acl-main.237
Bibkey:
Cite (ACL):
Lili Yu, Howard Chen, Sida I. Wang, Tao Lei, and Yoav Artzi. 2020. Interactive Classification by Asking Informative Questions. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 2664–2680, Online. Association for Computational Linguistics.
Cite (Informal):
Interactive Classification by Asking Informative Questions (Yu et al., ACL 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/starsem-semeval-split/2020.acl-main.237.pdf
Dataset:
 2020.acl-main.237.Dataset.pdf
Video:
 http://slideslive.com/38929271
Code
 asappresearch/interactive-classification