<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-lee-2023-draft">
    <titleInfo>
        <title>DRAFT: Dense Retrieval Augmented Few-shot Topic classifier Framework</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Keonwoo</namePart>
        <namePart type="family">Kim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Younggun</namePart>
        <namePart type="family">Lee</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>With the growing volume of diverse information, the demand for classifying arbitrary topics has become increasingly critical. To address this challenge, we introduce DRAFT, a simple framework designed to train a classifier for few-shot topic classification. DRAFT uses a few examples of a specific topic as queries to construct Customized dataset with a dense retriever model. Multi-query retrieval (MQR) algorithm, which effectively handles multiple queries related to a specific topic, is applied to construct the Customized dataset. Subsequently, we fine-tune a classifier using the Customized dataset to identify the topic. To demonstrate the efficacy of our proposed approach, we conduct evaluations on both widely used classification benchmark datasets and manually constructed datasets with 291 diverse topics, which simulate diverse contents encountered in real-world applications. DRAFT shows competitive or superior performance compared to baselines that use in-context learning, such as GPT-3 175B and InstructGPT 175B, on few-shot topic classification tasks despite having 177 times fewer parameters, demonstrating its effectiveness.</abstract>
    <identifier type="citekey">kim-lee-2023-draft</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-emnlp.150</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-emnlp.150</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>2278</start>
            <end>2294</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T DRAFT: Dense Retrieval Augmented Few-shot Topic classifier Framework
%A Kim, Keonwoo
%A Lee, Younggun
%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 kim-lee-2023-draft
%X With the growing volume of diverse information, the demand for classifying arbitrary topics has become increasingly critical. To address this challenge, we introduce DRAFT, a simple framework designed to train a classifier for few-shot topic classification. DRAFT uses a few examples of a specific topic as queries to construct Customized dataset with a dense retriever model. Multi-query retrieval (MQR) algorithm, which effectively handles multiple queries related to a specific topic, is applied to construct the Customized dataset. Subsequently, we fine-tune a classifier using the Customized dataset to identify the topic. To demonstrate the efficacy of our proposed approach, we conduct evaluations on both widely used classification benchmark datasets and manually constructed datasets with 291 diverse topics, which simulate diverse contents encountered in real-world applications. DRAFT shows competitive or superior performance compared to baselines that use in-context learning, such as GPT-3 175B and InstructGPT 175B, on few-shot topic classification tasks despite having 177 times fewer parameters, demonstrating its effectiveness.
%R 10.18653/v1/2023.findings-emnlp.150
%U https://aclanthology.org/2023.findings-emnlp.150
%U https://doi.org/10.18653/v1/2023.findings-emnlp.150
%P 2278-2294

Markdown (Informal)

[DRAFT: Dense Retrieval Augmented Few-shot Topic classifier Framework](https://aclanthology.org/2023.findings-emnlp.150) (Kim & Lee, Findings 2023)

• DRAFT: Dense Retrieval Augmented Few-shot Topic classifier Framework (Kim & Lee, Findings 2023)

ACL

• Keonwoo Kim and Younggun Lee. 2023. DRAFT: Dense Retrieval Augmented Few-shot Topic classifier Framework. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 2278–2294, Singapore. Association for Computational Linguistics.