Label-Agnostic Sequence Labeling by Copying Nearest Neighbors

Sam Wiseman, Karl Stratos


Abstract
Retrieve-and-edit based approaches to structured prediction, where structures associated with retrieved neighbors are edited to form new structures, have recently attracted increased interest. However, much recent work merely conditions on retrieved structures (e.g., in a sequence-to-sequence framework), rather than explicitly manipulating them. We show we can perform accurate sequence labeling by explicitly (and only) copying labels from retrieved neighbors. Moreover, because this copying is label-agnostic, we can achieve impressive performance in zero-shot sequence-labeling tasks. We additionally consider a dynamic programming approach to sequence labeling in the presence of retrieved neighbors, which allows for controlling the number of distinct (copied) segments used to form a prediction, and leads to both more interpretable and accurate predictions.
Anthology ID:
P19-1533
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Editors:
Anna Korhonen, David Traum, Lluís Màrquez
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5363–5369
Language:
URL:
https://aclanthology.org/P19-1533
DOI:
10.18653/v1/P19-1533
Bibkey:
Cite (ACL):
Sam Wiseman and Karl Stratos. 2019. Label-Agnostic Sequence Labeling by Copying Nearest Neighbors. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5363–5369, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Label-Agnostic Sequence Labeling by Copying Nearest Neighbors (Wiseman & Stratos, ACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/P19-1533.pdf
Code
 swiseman/neighbor-tagging
Data
CoNLL 2003Penn Treebank