Learning to Execute Actions or Ask Clarification Questions

Zhengxiang Shi, Yue Feng, Aldo Lipani


Abstract
Collaborative tasks are ubiquitous activities where a form of communication is required in order to reach a joint goal. Collaborative building is one of such tasks. We wish to develop an intelligent builder agent in a simulated building environment (Minecraft) that can build whatever users wish to build by just talking to the agent. In order to achieve this goal, such agents need to be able to take the initiative by asking clarification questions when further information is needed. Existing works on Minecraft Corpus Dataset only learn to execute instructions neglecting the importance of asking for clarifications. In this paper, we extend the Minecraft Corpus Dataset by annotating all builder utterances into eight types, including clarification questions, and propose a new builder agent model capable of determining when to ask or execute instructions. Experimental results show that our model achieves state-of-the-art performance on the collaborative building task with a substantial improvement. We also define two new tasks, the learning to ask task and the joint learning task. The latter consists of solving both collaborating building and learning to ask tasks jointly.
Anthology ID:
2022.findings-naacl.158
Volume:
Findings of the Association for Computational Linguistics: NAACL 2022
Month:
July
Year:
2022
Address:
Seattle, United States
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2060–2070
Language:
URL:
https://aclanthology.org/2022.findings-naacl.158
DOI:
10.18653/v1/2022.findings-naacl.158
Bibkey:
Cite (ACL):
Zhengxiang Shi, Yue Feng, and Aldo Lipani. 2022. Learning to Execute Actions or Ask Clarification Questions. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 2060–2070, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Learning to Execute Actions or Ask Clarification Questions (Shi et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-naacl.158.pdf
Video:
 https://aclanthology.org/2022.findings-naacl.158.mp4
Code
 zhengxiangshi/learntoask
Data
Extended Minecraft Corpus dataset