Constrained Decoding for Computationally Efficient Named Entity Recognition Taggers

Brian Lester, Daniel Pressel, Amy Hemmeter, Sagnik Ray Choudhury, Srinivas Bangalore


Abstract
Current state-of-the-art models for named entity recognition (NER) are neural models with a conditional random field (CRF) as the final layer. Entities are represented as per-token labels with a special structure in order to decode them into spans. Current work eschews prior knowledge of how the span encoding scheme works and relies on the CRF learning which transitions are illegal and which are not to facilitate global coherence. We find that by constraining the output to suppress illegal transitions we can train a tagger with a cross-entropy loss twice as fast as a CRF with differences in F1 that are statistically insignificant, effectively eliminating the need for a CRF. We analyze the dynamics of tag co-occurrence to explain when these constraints are most effective and provide open source implementations of our tagger in both PyTorch and TensorFlow.
Anthology ID:
2020.findings-emnlp.166
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2020
Month:
November
Year:
2020
Address:
Online
Editors:
Trevor Cohn, Yulan He, Yang Liu
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1841–1848
Language:
URL:
https://aclanthology.org/2020.findings-emnlp.166
DOI:
10.18653/v1/2020.findings-emnlp.166
Bibkey:
Cite (ACL):
Brian Lester, Daniel Pressel, Amy Hemmeter, Sagnik Ray Choudhury, and Srinivas Bangalore. 2020. Constrained Decoding for Computationally Efficient Named Entity Recognition Taggers. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 1841–1848, Online. Association for Computational Linguistics.
Cite (Informal):
Constrained Decoding for Computationally Efficient Named Entity Recognition Taggers (Lester et al., Findings 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.findings-emnlp.166.pdf
Optional supplementary material:
 2020.findings-emnlp.166.OptionalSupplementaryMaterial.zip
Video:
 https://slideslive.com/38940105
Code
 blester125/constrained-decoding
Data
CoNLL 2003SNIPSWNUT 2017