Partially Supervised Named Entity Recognition via the Expected Entity Ratio Loss

Thomas Effland, Michael Collins


Abstract
We study learning named entity recognizers in the presence of missing entity annotations. We approach this setting as tagging with latent variables and propose a novel loss, the Expected Entity Ratio, to learn models in the presence of systematically missing tags. We show that our approach is both theoretically sound and empirically useful. Experimentally, we find that it meets or exceeds performance of strong and state-of-the-art baselines across a variety of languages, annotation scenarios, and amounts of labeled data. In particular, we find that it significantly outperforms the previous state-of-the-art methods from Mayhew et al. (2019) and Li et al. (2021) by +12.7 and +2.3 F1 score in a challenging setting with only 1,000 biased annotations, averaged across 7 datasets. We also show that, when combined with our approach, a novel sparse annotation scheme outperforms exhaustive annotation for modest annotation budgets.1
Anthology ID:
2021.tacl-1.78
Volume:
Transactions of the Association for Computational Linguistics, Volume 9
Month:
Year:
2021
Address:
Cambridge, MA
Editors:
Brian Roark, Ani Nenkova
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
1320–1335
Language:
URL:
https://aclanthology.org/2021.tacl-1.78
DOI:
10.1162/tacl_a_00429
Bibkey:
Cite (ACL):
Thomas Effland and Michael Collins. 2021. Partially Supervised Named Entity Recognition via the Expected Entity Ratio Loss. Transactions of the Association for Computational Linguistics, 9:1320–1335.
Cite (Informal):
Partially Supervised Named Entity Recognition via the Expected Entity Ratio Loss (Effland & Collins, TACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.tacl-1.78.pdf
Video:
 https://aclanthology.org/2021.tacl-1.78.mp4