@inproceedings{dykes-etal-2024-leveraging,
title = "Leveraging High-Precision Corpus Queries for Text Classification via Large Language Models",
author = {Dykes, Nathan and
Evert, Stephanie and
Heinrich, Philipp and
Humml, Merlin and
Schr{\"o}der, Lutz},
editor = "Hautli-Janisz, Annette and
Lapesa, Gabriella and
Anastasiou, Lucas and
Gold, Valentin and
Liddo, Anna De and
Reed, Chris",
booktitle = "Proceedings of the First Workshop on Language-driven Deliberation Technology (DELITE) @ LREC-COLING 2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.delite-1.7",
pages = "52--57",
abstract = "We use query results from manually designed corpus queries for fine-tuning an LLM to identify argumentative fragments as a text mining task. The resulting model outperforms both an LLM fine-tuned on a relatively large manually annotated gold standard of tweets as well as a rule-based approach. This proof-of-concept study demonstrates the usefulness of corpus queries to generate training data for complex text categorisation tasks, especially if the targeted category has low prevalence (so that a manually annotated gold standard contains only a small number of positive examples).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dykes-etal-2024-leveraging">
<titleInfo>
<title>Leveraging High-Precision Corpus Queries for Text Classification via Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nathan</namePart>
<namePart type="family">Dykes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephanie</namePart>
<namePart type="family">Evert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Heinrich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Merlin</namePart>
<namePart type="family">Humml</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lutz</namePart>
<namePart type="family">Schröder</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 First Workshop on Language-driven Deliberation Technology (DELITE) @ LREC-COLING 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Annette</namePart>
<namePart type="family">Hautli-Janisz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriella</namePart>
<namePart type="family">Lapesa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucas</namePart>
<namePart type="family">Anastasiou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valentin</namePart>
<namePart type="family">Gold</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="given">De</namePart>
<namePart type="family">Liddo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Reed</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>We use query results from manually designed corpus queries for fine-tuning an LLM to identify argumentative fragments as a text mining task. The resulting model outperforms both an LLM fine-tuned on a relatively large manually annotated gold standard of tweets as well as a rule-based approach. This proof-of-concept study demonstrates the usefulness of corpus queries to generate training data for complex text categorisation tasks, especially if the targeted category has low prevalence (so that a manually annotated gold standard contains only a small number of positive examples).</abstract>
<identifier type="citekey">dykes-etal-2024-leveraging</identifier>
<location>
<url>https://aclanthology.org/2024.delite-1.7</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>52</start>
<end>57</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Leveraging High-Precision Corpus Queries for Text Classification via Large Language Models
%A Dykes, Nathan
%A Evert, Stephanie
%A Heinrich, Philipp
%A Humml, Merlin
%A Schröder, Lutz
%Y Hautli-Janisz, Annette
%Y Lapesa, Gabriella
%Y Anastasiou, Lucas
%Y Gold, Valentin
%Y Liddo, Anna De
%Y Reed, Chris
%S Proceedings of the First Workshop on Language-driven Deliberation Technology (DELITE) @ LREC-COLING 2024
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F dykes-etal-2024-leveraging
%X We use query results from manually designed corpus queries for fine-tuning an LLM to identify argumentative fragments as a text mining task. The resulting model outperforms both an LLM fine-tuned on a relatively large manually annotated gold standard of tweets as well as a rule-based approach. This proof-of-concept study demonstrates the usefulness of corpus queries to generate training data for complex text categorisation tasks, especially if the targeted category has low prevalence (so that a manually annotated gold standard contains only a small number of positive examples).
%U https://aclanthology.org/2024.delite-1.7
%P 52-57
Markdown (Informal)
[Leveraging High-Precision Corpus Queries for Text Classification via Large Language Models](https://aclanthology.org/2024.delite-1.7) (Dykes et al., DELITE 2024)
ACL