Computational Language Acquisition with Theory of Mind
Andy Liu, Hao Zhu, Emmy Liu, Yonatan Bisk, Graham Neubig

TL;DR
This paper explores how integrating a Theory of Mind mechanism into language-learning agents enhances their language acquisition, especially under more challenging tasks, drawing inspiration from child language development.
Contribution
It introduces a novel approach to computational language acquisition by incorporating a ToM-based internal listener model, demonstrating improved performance in language learning tasks.
Findings
Training with a ToM listener improves language performance.
Increased task difficulty leads to more fluent utterances.
ToM integration shows potential for advancing language acquisition models.
Abstract
Unlike current state-of-the-art language models, young children actively acquire language through interactions with their surrounding environment and caretakers. One mechanism that has been argued to be critical to language learning is the ability to infer the mental states of other agents in social environments, coined Theory of Mind (ToM) by Premack & Woodruff (1978). Drawing inspiration from the modern operationalized versions of ToM implemented in Rabinowitz et al. (2018) and Zhu et al. (2021), we build language-learning agents equipped with ToM, and measure its effects on the learning process. We model ToM by giving the speaker agent an internal listener model that is trained alongside the speaker and used to rerank potential utterances. We experiment with varying task difficulty, hypothesizing that models will acquire more complex language to adapt to stronger environmental…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
Taxonomy
TopicsTopic Modeling · Speech and dialogue systems · Natural Language Processing Techniques
