@inproceedings{kim-2020-deep,
title = "Deep Active Learning for Sequence Labeling Based on Diversity and Uncertainty in Gradient",
author = "Kim, Yekyung",
editor = "Campbell, William M. and
Waibel, Alex and
Hakkani-Tur, Dilek and
Hazen, Timothy J. and
Kilgour, Kevin and
Cho, Eunah and
Kumar, Varun and
Glaude, Hadrien",
booktitle = "Proceedings of the 2nd Workshop on Life-long Learning for Spoken Language Systems",
month = dec,
year = "2020",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.lifelongnlp-1.1",
pages = "1--8",
abstract = "Recently, several studies have investigated active learning (AL) for natural language processing tasks to alleviate data dependency. However, for query selection, most of these studies mainly rely on uncertainty-based sampling, which generally does not exploit the structural information of the unlabeled data. This leads to a sampling bias in the batch active learning setting, which selects several samples at once. In this work, we demonstrate that the amount of labeled training data can be reduced using active learning when it incorporates both uncertainty and diversity in the sequence labeling task. We examined the effects of our sequence-based approach by selecting weighted diverse in the gradient embedding approach across multiple tasks, datasets, models, and consistently outperform classic uncertainty-based sampling and diversity-based sampling.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-2020-deep">
<titleInfo>
<title>Deep Active Learning for Sequence Labeling Based on Diversity and Uncertainty in Gradient</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yekyung</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Life-long Learning for Spoken Language Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Campbell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Waibel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Timothy</namePart>
<namePart type="given">J</namePart>
<namePart type="family">Hazen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Kilgour</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eunah</namePart>
<namePart type="family">Cho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Varun</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hadrien</namePart>
<namePart type="family">Glaude</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recently, several studies have investigated active learning (AL) for natural language processing tasks to alleviate data dependency. However, for query selection, most of these studies mainly rely on uncertainty-based sampling, which generally does not exploit the structural information of the unlabeled data. This leads to a sampling bias in the batch active learning setting, which selects several samples at once. In this work, we demonstrate that the amount of labeled training data can be reduced using active learning when it incorporates both uncertainty and diversity in the sequence labeling task. We examined the effects of our sequence-based approach by selecting weighted diverse in the gradient embedding approach across multiple tasks, datasets, models, and consistently outperform classic uncertainty-based sampling and diversity-based sampling.</abstract>
<identifier type="citekey">kim-2020-deep</identifier>
<location>
<url>https://aclanthology.org/2020.lifelongnlp-1.1</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>1</start>
<end>8</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Deep Active Learning for Sequence Labeling Based on Diversity and Uncertainty in Gradient
%A Kim, Yekyung
%Y Campbell, William M.
%Y Waibel, Alex
%Y Hakkani-Tur, Dilek
%Y Hazen, Timothy J.
%Y Kilgour, Kevin
%Y Cho, Eunah
%Y Kumar, Varun
%Y Glaude, Hadrien
%S Proceedings of the 2nd Workshop on Life-long Learning for Spoken Language Systems
%D 2020
%8 December
%I Association for Computational Linguistics
%C Suzhou, China
%F kim-2020-deep
%X Recently, several studies have investigated active learning (AL) for natural language processing tasks to alleviate data dependency. However, for query selection, most of these studies mainly rely on uncertainty-based sampling, which generally does not exploit the structural information of the unlabeled data. This leads to a sampling bias in the batch active learning setting, which selects several samples at once. In this work, we demonstrate that the amount of labeled training data can be reduced using active learning when it incorporates both uncertainty and diversity in the sequence labeling task. We examined the effects of our sequence-based approach by selecting weighted diverse in the gradient embedding approach across multiple tasks, datasets, models, and consistently outperform classic uncertainty-based sampling and diversity-based sampling.
%U https://aclanthology.org/2020.lifelongnlp-1.1
%P 1-8
Markdown (Informal)
[Deep Active Learning for Sequence Labeling Based on Diversity and Uncertainty in Gradient](https://aclanthology.org/2020.lifelongnlp-1.1) (Kim, lifelongnlp 2020)
ACL