Enregistré dans:
Détails bibliographiques
Auteurs principaux: He, Jianfeng, Yu, Linlin, Lei, Shuo, Lu, Chang-Tien, Chen, Feng
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:https://arxiv.org/abs/2311.08726
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916275375046656
author He, Jianfeng
Yu, Linlin
Lei, Shuo
Lu, Chang-Tien
Chen, Feng
author_facet He, Jianfeng
Yu, Linlin
Lei, Shuo
Lu, Chang-Tien
Chen, Feng
contents 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 \url{https://github.com/he159ok/UncSeqLabeling_SLPN}.
format Preprint
id arxiv_https___arxiv_org_abs_2311_08726
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Uncertainty Estimation on Sequential Labeling via Uncertainty Transmission
He, Jianfeng
Yu, Linlin
Lei, Shuo
Lu, Chang-Tien
Chen, Feng
Computation and Language
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 \url{https://github.com/he159ok/UncSeqLabeling_SLPN}.
title Uncertainty Estimation on Sequential Labeling via Uncertainty Transmission
topic Computation and Language
url https://arxiv.org/abs/2311.08726