@inproceedings{wang-wang-2022-sentence,
title = "Sentence-Level Resampling for Named Entity Recognition",
author = "Wang, Xiaochen and
Wang, Yue",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.156",
doi = "10.18653/v1/2022.naacl-main.156",
pages = "2151--2165",
abstract = "As a fundamental task in natural language processing, named entity recognition (NER) aims to locate and classify named entities in unstructured text. However, named entities are always the minority among all tokens in the text. This data imbalance problem presents a challenge to machine learning models as their learning objective is usually dominated by the majority of non-entity tokens. To alleviate data imbalance, we propose a set of sentence-level resampling methods where the importance of each training sentence is computed based on its tokens and entities. We study the generalizability of these resampling methods on a wide variety of NER models (CRF, Bi-LSTM, and BERT) across corpora from diverse domains (general, social, and medical texts). Extensive experiments show that the proposed methods improve span-level macro F1-scores of the evaluated NER models on multiple corpora, frequently outperforming sub-sentence-level resampling, data augmentation, and special loss functions such as focal and Dice loss.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-wang-2022-sentence">
<titleInfo>
<title>Sentence-Level Resampling for Named Entity Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiaochen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>As a fundamental task in natural language processing, named entity recognition (NER) aims to locate and classify named entities in unstructured text. However, named entities are always the minority among all tokens in the text. This data imbalance problem presents a challenge to machine learning models as their learning objective is usually dominated by the majority of non-entity tokens. To alleviate data imbalance, we propose a set of sentence-level resampling methods where the importance of each training sentence is computed based on its tokens and entities. We study the generalizability of these resampling methods on a wide variety of NER models (CRF, Bi-LSTM, and BERT) across corpora from diverse domains (general, social, and medical texts). Extensive experiments show that the proposed methods improve span-level macro F1-scores of the evaluated NER models on multiple corpora, frequently outperforming sub-sentence-level resampling, data augmentation, and special loss functions such as focal and Dice loss.</abstract>
<identifier type="citekey">wang-wang-2022-sentence</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-main.156</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-main.156</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>2151</start>
<end>2165</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sentence-Level Resampling for Named Entity Recognition
%A Wang, Xiaochen
%A Wang, Yue
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F wang-wang-2022-sentence
%X As a fundamental task in natural language processing, named entity recognition (NER) aims to locate and classify named entities in unstructured text. However, named entities are always the minority among all tokens in the text. This data imbalance problem presents a challenge to machine learning models as their learning objective is usually dominated by the majority of non-entity tokens. To alleviate data imbalance, we propose a set of sentence-level resampling methods where the importance of each training sentence is computed based on its tokens and entities. We study the generalizability of these resampling methods on a wide variety of NER models (CRF, Bi-LSTM, and BERT) across corpora from diverse domains (general, social, and medical texts). Extensive experiments show that the proposed methods improve span-level macro F1-scores of the evaluated NER models on multiple corpora, frequently outperforming sub-sentence-level resampling, data augmentation, and special loss functions such as focal and Dice loss.
%R 10.18653/v1/2022.naacl-main.156
%U https://aclanthology.org/2022.naacl-main.156
%U https://doi.org/10.18653/v1/2022.naacl-main.156
%P 2151-2165
Markdown (Informal)
[Sentence-Level Resampling for Named Entity Recognition](https://aclanthology.org/2022.naacl-main.156) (Wang & Wang, NAACL 2022)
ACL
- Xiaochen Wang and Yue Wang. 2022. Sentence-Level Resampling for Named Entity Recognition. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2151–2165, Seattle, United States. Association for Computational Linguistics.