ALICE: Active Learning with Contrastive Natural Language Explanations

Weixin Liang, James Zou, Zhou Yu


Abstract
Training a supervised neural network classifier typically requires many annotated training samples. Collecting and annotating a large number of data points are costly and sometimes even infeasible. Traditional annotation process uses a low-bandwidth human-machine communication interface: classification labels, each of which only provides a few bits of information. We propose Active Learning with Contrastive Explanations (ALICE), an expert-in-the-loop training framework that utilizes contrastive natural language explanations to improve data efficiency in learning. AL-ICE learns to first use active learning to select the most informative pairs of label classes to elicit contrastive natural language explanations from experts. Then it extracts knowledge from these explanations using a semantic parser. Finally, it incorporates the extracted knowledge through dynamically changing the learning model’s structure. We applied ALICEin two visual recognition tasks, bird species classification and social relationship classification. We found by incorporating contrastive explanations, our models outperform baseline models that are trained with 40-100% more training data. We found that adding1expla-nation leads to similar performance gain as adding 13-30 labeled training data points.
Anthology ID:
2020.emnlp-main.355
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Editors:
Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4380–4391
Language:
URL:
https://aclanthology.org/2020.emnlp-main.355
DOI:
10.18653/v1/2020.emnlp-main.355
Bibkey:
Cite (ACL):
Weixin Liang, James Zou, and Zhou Yu. 2020. ALICE: Active Learning with Contrastive Natural Language Explanations. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 4380–4391, Online. Association for Computational Linguistics.
Cite (Informal):
ALICE: Active Learning with Contrastive Natural Language Explanations (Liang et al., EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.355.pdf
Video:
 https://slideslive.com/38938646
Data
CUB-200-2011