@inproceedings{zhao-rios-2024-utsa,
title = "{UTSA}-{NLP} at {C}hemo{T}imelines 2024: Evaluating Instruction-Tuned Language Models for Temporal Relation Extraction",
author = "Zhao, Xingmeng and
Rios, Anthony",
editor = "Naumann, Tristan and
Ben Abacha, Asma and
Bethard, Steven and
Roberts, Kirk and
Bitterman, Danielle",
booktitle = "Proceedings of the 6th Clinical Natural Language Processing Workshop",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.clinicalnlp-1.58",
doi = "10.18653/v1/2024.clinicalnlp-1.58",
pages = "604--615",
abstract = "This paper presents our approach for the 2024 ChemoTimelines shared task. Specifically, we explored using Large Language Models (LLMs) for temporal relation extraction. We evaluate multiple model variations based on how the training data is used. For instance, we transform the task into a question-answering problem and use QA pairs to extract chemo-related events and their temporal relations. Next, we add all the documents to each question-answer pair as examples in our training dataset. Finally, we explore adding unlabeled data for continued pretraining. Each addition is done iteratively. Our results show that adding the document helps, but unlabeled data does not yield performance improvements, possibly because we used only 1{\%} of the available data. Moreover, we find that instruction-tuned models still substantially underperform more traditional systems (e.g., EntityBERT).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhao-rios-2024-utsa">
<titleInfo>
<title>UTSA-NLP at ChemoTimelines 2024: Evaluating Instruction-Tuned Language Models for Temporal Relation Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xingmeng</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anthony</namePart>
<namePart type="family">Rios</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 6th Clinical Natural Language Processing Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tristan</namePart>
<namePart type="family">Naumann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asma</namePart>
<namePart type="family">Ben Abacha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kirk</namePart>
<namePart type="family">Roberts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danielle</namePart>
<namePart type="family">Bitterman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents our approach for the 2024 ChemoTimelines shared task. Specifically, we explored using Large Language Models (LLMs) for temporal relation extraction. We evaluate multiple model variations based on how the training data is used. For instance, we transform the task into a question-answering problem and use QA pairs to extract chemo-related events and their temporal relations. Next, we add all the documents to each question-answer pair as examples in our training dataset. Finally, we explore adding unlabeled data for continued pretraining. Each addition is done iteratively. Our results show that adding the document helps, but unlabeled data does not yield performance improvements, possibly because we used only 1% of the available data. Moreover, we find that instruction-tuned models still substantially underperform more traditional systems (e.g., EntityBERT).</abstract>
<identifier type="citekey">zhao-rios-2024-utsa</identifier>
<identifier type="doi">10.18653/v1/2024.clinicalnlp-1.58</identifier>
<location>
<url>https://aclanthology.org/2024.clinicalnlp-1.58</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>604</start>
<end>615</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UTSA-NLP at ChemoTimelines 2024: Evaluating Instruction-Tuned Language Models for Temporal Relation Extraction
%A Zhao, Xingmeng
%A Rios, Anthony
%Y Naumann, Tristan
%Y Ben Abacha, Asma
%Y Bethard, Steven
%Y Roberts, Kirk
%Y Bitterman, Danielle
%S Proceedings of the 6th Clinical Natural Language Processing Workshop
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F zhao-rios-2024-utsa
%X This paper presents our approach for the 2024 ChemoTimelines shared task. Specifically, we explored using Large Language Models (LLMs) for temporal relation extraction. We evaluate multiple model variations based on how the training data is used. For instance, we transform the task into a question-answering problem and use QA pairs to extract chemo-related events and their temporal relations. Next, we add all the documents to each question-answer pair as examples in our training dataset. Finally, we explore adding unlabeled data for continued pretraining. Each addition is done iteratively. Our results show that adding the document helps, but unlabeled data does not yield performance improvements, possibly because we used only 1% of the available data. Moreover, we find that instruction-tuned models still substantially underperform more traditional systems (e.g., EntityBERT).
%R 10.18653/v1/2024.clinicalnlp-1.58
%U https://aclanthology.org/2024.clinicalnlp-1.58
%U https://doi.org/10.18653/v1/2024.clinicalnlp-1.58
%P 604-615
Markdown (Informal)
[UTSA-NLP at ChemoTimelines 2024: Evaluating Instruction-Tuned Language Models for Temporal Relation Extraction](https://aclanthology.org/2024.clinicalnlp-1.58) (Zhao & Rios, ClinicalNLP-WS 2024)
ACL