Learning a Policy for Opportunistic Active Learning

Aishwarya Padmakumar, Peter Stone, Raymond Mooney


Abstract
Active learning identifies data points to label that are expected to be the most useful in improving a supervised model. Opportunistic active learning incorporates active learning into interactive tasks that constrain possible queries during interactions. Prior work has shown that opportunistic active learning can be used to improve grounding of natural language descriptions in an interactive object retrieval task. In this work, we use reinforcement learning for such an object retrieval task, to learn a policy that effectively trades off task completion with model improvement that would benefit future tasks.
Anthology ID:
D18-1165
Volume:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Month:
October-November
Year:
2018
Address:
Brussels, Belgium
Editors:
Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1347–1357
Language:
URL:
https://aclanthology.org/D18-1165
DOI:
10.18653/v1/D18-1165
Bibkey:
Cite (ACL):
Aishwarya Padmakumar, Peter Stone, and Raymond Mooney. 2018. Learning a Policy for Opportunistic Active Learning. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 1347–1357, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Learning a Policy for Opportunistic Active Learning (Padmakumar et al., EMNLP 2018)
Copy Citation:
PDF:
https://aclanthology.org/D18-1165.pdf
Attachment:
 D18-1165.Attachment.tgz
Video:
 https://aclanthology.org/D18-1165.mp4
Data
Visual Genome