Continual Learning for Grounded Instruction Generation by Observing Human Following Behavior

Noriyuki Kojima, Alane Suhr, Yoav Artzi


Abstract
We study continual learning for natural language instruction generation, by observing human users’ instruction execution. We focus on a collaborative scenario, where the system both acts and delegates tasks to human users using natural language. We compare user execution of generated instructions to the original system intent as an indication to the system’s success communicating its intent. We show how to use this signal to improve the system’s ability to generate instructions via contextual bandit learning. In interaction with real users, our system demonstrates dramatic improvements in its ability to generate language over time.
Anthology ID:
2021.tacl-1.77
Volume:
Transactions of the Association for Computational Linguistics, Volume 9
Month:
Year:
2021
Address:
Cambridge, MA
Editors:
Brian Roark, Ani Nenkova
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
1303–1319
Language:
URL:
https://aclanthology.org/2021.tacl-1.77
DOI:
10.1162/tacl_a_00428
Bibkey:
Cite (ACL):
Noriyuki Kojima, Alane Suhr, and Yoav Artzi. 2021. Continual Learning for Grounded Instruction Generation by Observing Human Following Behavior. Transactions of the Association for Computational Linguistics, 9:1303–1319.
Cite (Informal):
Continual Learning for Grounded Instruction Generation by Observing Human Following Behavior (Kojima et al., TACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.tacl-1.77.pdf
Video:
 https://aclanthology.org/2021.tacl-1.77.mp4