Sequence classification with human attention
View / Open Files
Authors
Barrett, M
Bingel, J
Hollenstein, N
Rei, Marek
Søgaard, A
Publication Date
2018Journal Title
CoNLL 2018 - 22nd Conference on Computational Natural Language Learning, Proceedings
Conference Name
Proceedings of the 22nd Conference on Computational Natural Language Learning
ISBN
9781948087728
Publisher
Association for Computational Linguistics
Pages
302-312
Type
Conference Object
This Version
AM
Metadata
Show full item recordCitation
Barrett, M., Bingel, J., Hollenstein, N., Rei, M., & Søgaard, A. (2018). Sequence classification with human attention. CoNLL 2018 - 22nd Conference on Computational Natural Language Learning, Proceedings, 302-312. https://doi.org/10.18653/v1/k18-1030
Abstract
Learning attention functions requires large volumes of data, but many NLP tasks simulate human behavior, and in this paper, we show that human attention really does provide a good inductive bias on many attention functions in NLP. Specifically, we use estimated human attention derived from eye-tracking corpora to regularize attention functions in recurrent neural networks. We show substantial improvements across a range of tasks, including sentiment analysis, grammatical error detection, and detection of abusive language.
Sponsorship
Cambridge Assessment (unknown)
Identifiers
External DOI: https://doi.org/10.18653/v1/k18-1030
This record's URL: https://www.repository.cam.ac.uk/handle/1810/287996
Rights
Licence:
http://www.rioxx.net/licenses/all-rights-reserved
Statistics
Total file downloads (since January 2020). For more information on metrics see the
IRUS guide.