Dear Spiral user, We’re pleased to introduce Helix, https://helix.imperial.ac.uk/ Imperial’s new repository for research datasets. Please use Helix for all future dataset deposits. There is no change to Spiral - continue depositing as usual. For queries, contact the Research Data Management team at rdm-enquiries@imperial.ac.uk. Kind regards, the Spiral Team. The Spiral team
Zero-shot sequence labeling: transferring knowledge from sentences to tokens
File(s)
N18-1027.pdf (316.58 KB)
Published version
OA Location
Author(s)
Rei, Marek
Søgaard, Anders
Type
Conference Paper
Abstract
Can attention- or gradient-based visualization techniques be used to infer token-level labels for binary sequence tagging problems, using networks trained only on sentence-level labels? We construct a neural network architecture based on soft attention, train it as a binary sentence classifier and evaluate against token-level annotation on four different datasets. Inferring token labels from a network provides a method for quantitatively evaluating what the model is learning, along with generating useful feedback in assistance systems. Our results indicate that attention-based methods are able to predict token-level labels more accurately, compared to gradient-based methods, sometimes even rivaling the supervised oracle network.
Date Issued
2018-06-01
Date Acceptance
2018-06-01
Citation
Proceedings of the 2018 Conference of the North American Chapter of
the Association for Computational Linguistics: Human Language
Technologies, Volume 1 (Long Papers), 2018, Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pp.293-302
URI
URL
DOI
Publisher
Association for Computational Linguistics
Start Page
293
End Page
302
Journal / Book Title
Proceedings of the 2018 Conference of the North American Chapter of
the Association for Computational Linguistics: Human Language
Technologies, Volume 1 (Long Papers)
Volume
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)
Copyright Statement
© 2018 Association for Computational Linguistics. Materials published in or after 2016 are licensed on a Creative Commons Attribution 4.0 International License.
License URL
Identifier
https://www.aclweb.org/anthology/N18-1027/
Source
Proceedings of the 2018 Conference of the North American Chapter of
the Association for Computational Linguistics: Human Language
Technologies, Volume 1 (Long Papers)
Publication Status
Published
Start Date
2018-06-01
Finish Date
2018-06-06
Coverage Spatial
New Orleans, Louisiana
Date Publish Online
2018-06-01