Uncertainty Estimation on Sequential Labeling via Uncertainty Transmission

Jianfeng He, Linlin Yu, Shuo Lei, Chang-Tien Lu, Feng Chen


Abstract
Sequential labeling is a task predicting labels for each token in a sequence, such as Named Entity Recognition (NER). NER tasks aim to extract entities and predict their labels given a text, which is important in information extraction. Although previous works have shown great progress in improving NER performance, uncertainty estimation on NER (UE-NER) is still underexplored but essential. This work focuses on UE-NER, which aims to estimate uncertainty scores for the NER predictions. Previous uncertainty estimation models often overlook two unique characteristics of NER: the connection between entities (i.e., one entity embedding is learned based on the other ones) and wrong span cases in the entity extraction subtask. Therefore, we propose a Sequential Labeling Posterior Network (SLPN) to estimate uncertainty scores for the extracted entities, considering uncertainty transmitted from other tokens. Moreover, we have defined an evaluation strategy to address the specificity of wrong-span cases. Our SLPN has achieved significant improvements on three datasets, such as a 5.54-point improvement in AUPR on the MIT-Restaurant dataset. Our code is available at https://github.com/he159ok/UncSeqLabeling_SLPN.
Anthology ID:
2024.findings-naacl.180
Volume:
Findings of the Association for Computational Linguistics: NAACL 2024
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2823–2835
Language:
URL:
https://aclanthology.org/2024.findings-naacl.180
DOI:
Bibkey:
Cite (ACL):
Jianfeng He, Linlin Yu, Shuo Lei, Chang-Tien Lu, and Feng Chen. 2024. Uncertainty Estimation on Sequential Labeling via Uncertainty Transmission. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 2823–2835, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Uncertainty Estimation on Sequential Labeling via Uncertainty Transmission (He et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-naacl.180.pdf
Copyright:
 2024.findings-naacl.180.copyright.pdf