@inproceedings{wang-etal-2023-knowcomp,
title = "{K}now{C}omp at {S}em{E}val-2023 Task 7: Fine-tuning Pre-trained Language Models for Clinical Trial Entailment Identification",
author = "Wang, Weiqi and
Xu, Baixuan and
Fang, Tianqing and
Zhang, Lirong and
Song, Yangqiu",
editor = {Ojha, Atul Kr. and
Do{\u{g}}ru{\"o}z, A. Seza and
Da San Martino, Giovanni and
Tayyar Madabushi, Harish and
Kumar, Ritesh and
Sartori, Elisa},
booktitle = "Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.semeval-1.1",
doi = "10.18653/v1/2023.semeval-1.1",
pages = "1--9",
abstract = "In this paper, we present our system for the textual entailment identification task as a subtask of the SemEval-2023 Task 7: Multi-evidence Natural Language Inference for Clinical Trial Data. The entailment identification task aims to determine whether a medical statement affirms a valid entailment given a clinical trial premise or forms a contradiction with it. Since the task is inherently a text classification task, we propose a system that performs binary classification given a statement and its associated clinical trial. Our proposed system leverages a human-defined prompt to aggregate the information contained in the statement, section name, and clinical trials. Pre-trained language models are then finetuned on the prompted input sentences to learn to discriminate the inference relation between the statement and clinical trial. To validate our system, we conduct extensive experiments with a wide variety of pre-trained language models. Our best system is built on DeBERTa-v3-large, which achieves an F1 score of 0.764 and secures the fifth rank in the official leaderboard.Further analysis indicates that leveraging our designed prompt is effective, and our model suffers from a low recall. Our code and pre-trained models are available at [\url{https://github.com/HKUST-KnowComp/NLI4CT}](\url{https://github.com/HKUST-KnowComp/NLI4CT}).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2023-knowcomp">
<titleInfo>
<title>KnowComp at SemEval-2023 Task 7: Fine-tuning Pre-trained Language Models for Clinical Trial Entailment Identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Weiqi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Baixuan</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianqing</namePart>
<namePart type="family">Fang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lirong</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yangqiu</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="given">Seza</namePart>
<namePart type="family">Doğruöz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giovanni</namePart>
<namePart type="family">Da San Martino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harish</namePart>
<namePart type="family">Tayyar Madabushi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elisa</namePart>
<namePart type="family">Sartori</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we present our system for the textual entailment identification task as a subtask of the SemEval-2023 Task 7: Multi-evidence Natural Language Inference for Clinical Trial Data. The entailment identification task aims to determine whether a medical statement affirms a valid entailment given a clinical trial premise or forms a contradiction with it. Since the task is inherently a text classification task, we propose a system that performs binary classification given a statement and its associated clinical trial. Our proposed system leverages a human-defined prompt to aggregate the information contained in the statement, section name, and clinical trials. Pre-trained language models are then finetuned on the prompted input sentences to learn to discriminate the inference relation between the statement and clinical trial. To validate our system, we conduct extensive experiments with a wide variety of pre-trained language models. Our best system is built on DeBERTa-v3-large, which achieves an F1 score of 0.764 and secures the fifth rank in the official leaderboard.Further analysis indicates that leveraging our designed prompt is effective, and our model suffers from a low recall. Our code and pre-trained models are available at [https://github.com/HKUST-KnowComp/NLI4CT](https://github.com/HKUST-KnowComp/NLI4CT).</abstract>
<identifier type="citekey">wang-etal-2023-knowcomp</identifier>
<identifier type="doi">10.18653/v1/2023.semeval-1.1</identifier>
<location>
<url>https://aclanthology.org/2023.semeval-1.1</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>1</start>
<end>9</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T KnowComp at SemEval-2023 Task 7: Fine-tuning Pre-trained Language Models for Clinical Trial Entailment Identification
%A Wang, Weiqi
%A Xu, Baixuan
%A Fang, Tianqing
%A Zhang, Lirong
%A Song, Yangqiu
%Y Ojha, Atul Kr.
%Y Doğruöz, A. Seza
%Y Da San Martino, Giovanni
%Y Tayyar Madabushi, Harish
%Y Kumar, Ritesh
%Y Sartori, Elisa
%S Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F wang-etal-2023-knowcomp
%X In this paper, we present our system for the textual entailment identification task as a subtask of the SemEval-2023 Task 7: Multi-evidence Natural Language Inference for Clinical Trial Data. The entailment identification task aims to determine whether a medical statement affirms a valid entailment given a clinical trial premise or forms a contradiction with it. Since the task is inherently a text classification task, we propose a system that performs binary classification given a statement and its associated clinical trial. Our proposed system leverages a human-defined prompt to aggregate the information contained in the statement, section name, and clinical trials. Pre-trained language models are then finetuned on the prompted input sentences to learn to discriminate the inference relation between the statement and clinical trial. To validate our system, we conduct extensive experiments with a wide variety of pre-trained language models. Our best system is built on DeBERTa-v3-large, which achieves an F1 score of 0.764 and secures the fifth rank in the official leaderboard.Further analysis indicates that leveraging our designed prompt is effective, and our model suffers from a low recall. Our code and pre-trained models are available at [https://github.com/HKUST-KnowComp/NLI4CT](https://github.com/HKUST-KnowComp/NLI4CT).
%R 10.18653/v1/2023.semeval-1.1
%U https://aclanthology.org/2023.semeval-1.1
%U https://doi.org/10.18653/v1/2023.semeval-1.1
%P 1-9
Markdown (Informal)
[KnowComp at SemEval-2023 Task 7: Fine-tuning Pre-trained Language Models for Clinical Trial Entailment Identification](https://aclanthology.org/2023.semeval-1.1) (Wang et al., SemEval 2023)
ACL