@inproceedings{luo-etal-2023-weighting,
title = "Re-weighting Tokens: A Simple and Effective Active Learning Strategy for Named Entity Recognition",
author = "Luo, Haocheng and
Tan, Wei and
Nguyen, Ngoc and
Du, Lan",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.847/",
doi = "10.18653/v1/2023.findings-emnlp.847",
pages = "12725--12734",
abstract = "Active learning, a widely adopted technique for enhancing machine learning models in text and image classification tasks with limited annotation resources, has received relatively little attention in the domain of Named Entity Recognition (NER). The challenge of data imbalance in NER has hindered the effectiveness of active learning, as sequence labellers lack sufficient learning signals. To address these challenges, this paper presents a novel re-weighting-based active learning strategy that assigns dynamic smoothing weights to individual tokens. This adaptable strategy is compatible with various token-level acquisition functions and contributes to the development of robust active learners. Experimental results on multiple corpora demonstrate the substantial performance improvement achieved by incorporating our re-weighting strategy into existing acquisition functions, validating its practical efficacy. We will release our implementation upon the publication of this paper."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="luo-etal-2023-weighting">
<titleInfo>
<title>Re-weighting Tokens: A Simple and Effective Active Learning Strategy for Named Entity Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haocheng</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ngoc</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lan</namePart>
<namePart type="family">Du</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Active learning, a widely adopted technique for enhancing machine learning models in text and image classification tasks with limited annotation resources, has received relatively little attention in the domain of Named Entity Recognition (NER). The challenge of data imbalance in NER has hindered the effectiveness of active learning, as sequence labellers lack sufficient learning signals. To address these challenges, this paper presents a novel re-weighting-based active learning strategy that assigns dynamic smoothing weights to individual tokens. This adaptable strategy is compatible with various token-level acquisition functions and contributes to the development of robust active learners. Experimental results on multiple corpora demonstrate the substantial performance improvement achieved by incorporating our re-weighting strategy into existing acquisition functions, validating its practical efficacy. We will release our implementation upon the publication of this paper.</abstract>
<identifier type="citekey">luo-etal-2023-weighting</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.847</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.847/</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>12725</start>
<end>12734</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Re-weighting Tokens: A Simple and Effective Active Learning Strategy for Named Entity Recognition
%A Luo, Haocheng
%A Tan, Wei
%A Nguyen, Ngoc
%A Du, Lan
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F luo-etal-2023-weighting
%X Active learning, a widely adopted technique for enhancing machine learning models in text and image classification tasks with limited annotation resources, has received relatively little attention in the domain of Named Entity Recognition (NER). The challenge of data imbalance in NER has hindered the effectiveness of active learning, as sequence labellers lack sufficient learning signals. To address these challenges, this paper presents a novel re-weighting-based active learning strategy that assigns dynamic smoothing weights to individual tokens. This adaptable strategy is compatible with various token-level acquisition functions and contributes to the development of robust active learners. Experimental results on multiple corpora demonstrate the substantial performance improvement achieved by incorporating our re-weighting strategy into existing acquisition functions, validating its practical efficacy. We will release our implementation upon the publication of this paper.
%R 10.18653/v1/2023.findings-emnlp.847
%U https://aclanthology.org/2023.findings-emnlp.847/
%U https://doi.org/10.18653/v1/2023.findings-emnlp.847
%P 12725-12734
Markdown (Informal)
[Re-weighting Tokens: A Simple and Effective Active Learning Strategy for Named Entity Recognition](https://aclanthology.org/2023.findings-emnlp.847/) (Luo et al., Findings 2023)
ACL