Instance-Based Learning of Span Representations: A Case Study through Named Entity Recognition

Hiroki Ouchi, Jun Suzuki, Sosuke Kobayashi, Sho Yokoi, Tatsuki Kuribayashi, Ryuto Konno, Kentaro Inui


Abstract
Interpretable rationales for model predictions play a critical role in practical applications. In this study, we develop models possessing interpretable inference process for structured prediction. Specifically, we present a method of instance-based learning that learns similarities between spans. At inference time, each span is assigned a class label based on its similar spans in the training set, where it is easy to understand how much each training instance contributes to the predictions. Through empirical analysis on named entity recognition, we demonstrate that our method enables to build models that have high interpretability without sacrificing performance.
Anthology ID:
2020.acl-main.575
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Editors:
Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6452–6459
Language:
URL:
https://aclanthology.org/2020.acl-main.575
DOI:
10.18653/v1/2020.acl-main.575
Bibkey:
Cite (ACL):
Hiroki Ouchi, Jun Suzuki, Sosuke Kobayashi, Sho Yokoi, Tatsuki Kuribayashi, Ryuto Konno, and Kentaro Inui. 2020. Instance-Based Learning of Span Representations: A Case Study through Named Entity Recognition. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 6452–6459, Online. Association for Computational Linguistics.
Cite (Informal):
Instance-Based Learning of Span Representations: A Case Study through Named Entity Recognition (Ouchi et al., ACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-main.575.pdf
Video:
 http://slideslive.com/38928957
Code
 hiroki13/instance-based-ner
Data
CoNLL 2003