@inproceedings{kotian-etal-2024-taal,
title = "{TAAL}: Target-Aware Active Learning",
author = "Kotian, Kunal and
Bhattacharya, Indranil and
Gupta, Shikhar and
Pavani, Kaushik and
Bhandari, Naval and
Dasgupta, Sunny",
editor = "Malmasi, Shervin and
Fetahu, Besnik and
Ueffing, Nicola and
Rokhlenko, Oleg and
Agichtein, Eugene and
Guy, Ido",
booktitle = "Proceedings of the Seventh Workshop on e-Commerce and NLP @ LREC-COLING 2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.ecnlp-1.14",
pages = "136--144",
abstract = "Pool-based active learning techniques have had success producing multi-class classifiers that achieve high accuracy with fewer labels com- pared to random labeling. However, in an industrial setting where we often have class-level business targets to achieve (e.g., 95{\%} recall at 95{\%} precision for each class), active learning techniques continue to acquire labels for classes that have already met their targets, thus consuming unnecessary manual annotations. We address this problem by proposing a framework called Target-Aware Active Learning that converts any active learning query strategy into its target-aware variant by leveraging the gap between each class{'} current estimated accuracy and its corresponding business target. We show empirically that target-aware variants of state-of-the-art active learning techniques achieve business targets faster on 2 open-source image classification datasets and 2 proprietary product classification datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kotian-etal-2024-taal">
<titleInfo>
<title>TAAL: Target-Aware Active Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kunal</namePart>
<namePart type="family">Kotian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Indranil</namePart>
<namePart type="family">Bhattacharya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shikhar</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaushik</namePart>
<namePart type="family">Pavani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naval</namePart>
<namePart type="family">Bhandari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunny</namePart>
<namePart type="family">Dasgupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh Workshop on e-Commerce and NLP @ LREC-COLING 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shervin</namePart>
<namePart type="family">Malmasi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Besnik</namePart>
<namePart type="family">Fetahu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicola</namePart>
<namePart type="family">Ueffing</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oleg</namePart>
<namePart type="family">Rokhlenko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eugene</namePart>
<namePart type="family">Agichtein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ido</namePart>
<namePart type="family">Guy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Pool-based active learning techniques have had success producing multi-class classifiers that achieve high accuracy with fewer labels com- pared to random labeling. However, in an industrial setting where we often have class-level business targets to achieve (e.g., 95% recall at 95% precision for each class), active learning techniques continue to acquire labels for classes that have already met their targets, thus consuming unnecessary manual annotations. We address this problem by proposing a framework called Target-Aware Active Learning that converts any active learning query strategy into its target-aware variant by leveraging the gap between each class’ current estimated accuracy and its corresponding business target. We show empirically that target-aware variants of state-of-the-art active learning techniques achieve business targets faster on 2 open-source image classification datasets and 2 proprietary product classification datasets.</abstract>
<identifier type="citekey">kotian-etal-2024-taal</identifier>
<location>
<url>https://aclanthology.org/2024.ecnlp-1.14</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>136</start>
<end>144</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TAAL: Target-Aware Active Learning
%A Kotian, Kunal
%A Bhattacharya, Indranil
%A Gupta, Shikhar
%A Pavani, Kaushik
%A Bhandari, Naval
%A Dasgupta, Sunny
%Y Malmasi, Shervin
%Y Fetahu, Besnik
%Y Ueffing, Nicola
%Y Rokhlenko, Oleg
%Y Agichtein, Eugene
%Y Guy, Ido
%S Proceedings of the Seventh Workshop on e-Commerce and NLP @ LREC-COLING 2024
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F kotian-etal-2024-taal
%X Pool-based active learning techniques have had success producing multi-class classifiers that achieve high accuracy with fewer labels com- pared to random labeling. However, in an industrial setting where we often have class-level business targets to achieve (e.g., 95% recall at 95% precision for each class), active learning techniques continue to acquire labels for classes that have already met their targets, thus consuming unnecessary manual annotations. We address this problem by proposing a framework called Target-Aware Active Learning that converts any active learning query strategy into its target-aware variant by leveraging the gap between each class’ current estimated accuracy and its corresponding business target. We show empirically that target-aware variants of state-of-the-art active learning techniques achieve business targets faster on 2 open-source image classification datasets and 2 proprietary product classification datasets.
%U https://aclanthology.org/2024.ecnlp-1.14
%P 136-144
Markdown (Informal)
[TAAL: Target-Aware Active Learning](https://aclanthology.org/2024.ecnlp-1.14) (Kotian et al., ECNLP-WS 2024)
ACL
- Kunal Kotian, Indranil Bhattacharya, Shikhar Gupta, Kaushik Pavani, Naval Bhandari, and Sunny Dasgupta. 2024. TAAL: Target-Aware Active Learning. In Proceedings of the Seventh Workshop on e-Commerce and NLP @ LREC-COLING 2024, pages 136–144, Torino, Italia. ELRA and ICCL.