Calibrate your listeners! Robust communication-based training for pragmatic speakers

Rose Wang, Julia White, Jesse Mu, Noah Goodman


Abstract
To be good conversational partners, natural language processing (NLP) systems should be trained to produce contextually useful utterances. Prior work has investigated training NLP systems with communication-based objectives, where a neural listener stands in as a communication partner. However, these systems commonly suffer from semantic drift where the learned language diverges radically from natural language. We propose a method that uses a population of neural listeners to regularize speaker training. We first show that language drift originates from the poor uncertainty calibration of a neural listener, which makes high-certainty predictions on novel sentences. We explore ensemble- and dropout-based populations of listeners and find that the former results in better uncertainty quantification. We evaluate both population-based objectives on reference games, and show that the ensemble method with better calibration enables the speaker to generate pragmatic utterances while scaling to a large vocabulary and generalizing to new games and listeners.
Anthology ID:
2021.findings-emnlp.83
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2021
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
Findings
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
977–984
Language:
URL:
https://aclanthology.org/2021.findings-emnlp.83
DOI:
10.18653/v1/2021.findings-emnlp.83
Bibkey:
Cite (ACL):
Rose Wang, Julia White, Jesse Mu, and Noah Goodman. 2021. Calibrate your listeners! Robust communication-based training for pragmatic speakers. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 977–984, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Calibrate your listeners! Robust communication-based training for pragmatic speakers (Wang et al., Findings 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.findings-emnlp.83.pdf
Video:
 https://aclanthology.org/2021.findings-emnlp.83.mp4
Code
 rosewang2008/calibrate_your_listeners
Data
ShapeWorld