Learning how to Learn: An Adaptive Dialogue Agent for Incrementally Learning Visually Grounded Word Meanings

Yanchao Yu, Arash Eshghi, Oliver Lemon


Abstract
We present an optimised multi-modal dialogue agent for interactive learning of visually grounded word meanings from a human tutor, trained on real human-human tutoring data. Within a life-long interactive learning period, the agent, trained using Reinforcement Learning (RL), must be able to handle natural conversations with human users, and achieve good learning performance (i.e. accuracy) while minimising human effort in the learning process. We train and evaluate this system in interaction with a simulated human tutor, which is built on the BURCHAK corpus – a Human-Human Dialogue dataset for the visual learning task. The results show that: 1) The learned policy can coherently interact with the simulated user to achieve the goal of the task (i.e. learning visual attributes of objects, e.g. colour and shape); and 2) it finds a better trade-off between classifier accuracy and tutoring costs than hand-crafted rule-based policies, including ones with dynamic policies.
Anthology ID:
W17-2802
Volume:
Proceedings of the First Workshop on Language Grounding for Robotics
Month:
August
Year:
2017
Address:
Vancouver, Canada
Editors:
Mohit Bansal, Cynthia Matuszek, Jacob Andreas, Yoav Artzi, Yonatan Bisk
Venue:
RoboNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
10–19
Language:
URL:
https://aclanthology.org/W17-2802
DOI:
10.18653/v1/W17-2802
Bibkey:
Cite (ACL):
Yanchao Yu, Arash Eshghi, and Oliver Lemon. 2017. Learning how to Learn: An Adaptive Dialogue Agent for Incrementally Learning Visually Grounded Word Meanings. In Proceedings of the First Workshop on Language Grounding for Robotics, pages 10–19, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
Learning how to Learn: An Adaptive Dialogue Agent for Incrementally Learning Visually Grounded Word Meanings (Yu et al., RoboNLP 2017)
Copy Citation:
PDF:
https://aclanthology.org/W17-2802.pdf