Deriving Machine Attention from Human Rationales

Yujia Bao, Shiyu Chang, Mo Yu, Regina Barzilay


Abstract
Attention-based models are successful when trained on large amounts of data. In this paper, we demonstrate that even in the low-resource scenario, attention can be learned effectively. To this end, we start with discrete human-annotated rationales and map them into continuous attention. Our central hypothesis is that this mapping is general across domains, and thus can be transferred from resource-rich domains to low-resource ones. Our model jointly learns a domain-invariant representation and induces the desired mapping between rationales and attention. Our empirical results validate this hypothesis and show that our approach delivers significant gains over state-of-the-art baselines, yielding over 15% average error reduction on benchmark datasets.
Anthology ID:
D18-1216
Volume:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Month:
October-November
Year:
2018
Address:
Brussels, Belgium
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1903–1913
Language:
URL:
https://aclanthology.org/D18-1216
DOI:
10.18653/v1/D18-1216
Bibkey:
Cite (ACL):
Yujia Bao, Shiyu Chang, Mo Yu, and Regina Barzilay. 2018. Deriving Machine Attention from Human Rationales. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 1903–1913, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Deriving Machine Attention from Human Rationales (Bao et al., EMNLP 2018)
Copy Citation:
PDF:
https://aclanthology.org/D18-1216.pdf
Attachment:
 D18-1216.Attachment.zip
Video:
 https://vimeo.com/305661928
Code
 YujiaBao/R2A +  additional community code