@inproceedings{zhao-etal-2023-hw,
title = "{HW}-{TSC} at {S}em{E}val-2023 Task 7: Exploring the Natural Language Inference Capabilities of {C}hat{GPT} and Pre-trained Language Model for Clinical Trial",
author = "Zhao, Xiaofeng and
Zhang, Min and
Ma, Miaomiao and
Su, Chang and
Liu, Yilun and
Wang, Minghan and
Qiao, Xiaosong and
Guo, Jiaxin and
Li, Yinglu and
Ma, Wenbing",
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-1.221",
doi = "10.18653/v1/2023.semeval-1.221",
pages = "1603--1608",
abstract = "In this paper, we describe the multi strategy system for SemEval-2022 Task 7, This task aims to determine whether a given statement is supported by one or two Clinical Trial reports, and to identify evidence that supports the statement. This is a task that requires high natural language inference capabilities. In Subtask 1, we compare our strategy based on prompt learning and ChatGPT with a baseline constructed using BERT in zero-shot setting, and validate the effectiveness of our strategy. In Subtask 2, we fine-tune DeBERTaV3 for classification without relying on the results from Subtask 1, and we observe that early stopping can effectively prevent model overfitting, which performs well in Subtask 2. In addition, we did not use any ensemble strategies. Ultimately, we achieved the 10th place in Subtask 1 and the 2nd place in Subtask 2.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhao-etal-2023-hw">
<titleInfo>
<title>HW-TSC at SemEval-2023 Task 7: Exploring the Natural Language Inference Capabilities of ChatGPT and Pre-trained Language Model for Clinical Trial</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiaofeng</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miaomiao</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chang</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yilun</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaosong</namePart>
<namePart type="family">Qiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaxin</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yinglu</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenbing</namePart>
<namePart type="family">Ma</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 describe the multi strategy system for SemEval-2022 Task 7, This task aims to determine whether a given statement is supported by one or two Clinical Trial reports, and to identify evidence that supports the statement. This is a task that requires high natural language inference capabilities. In Subtask 1, we compare our strategy based on prompt learning and ChatGPT with a baseline constructed using BERT in zero-shot setting, and validate the effectiveness of our strategy. In Subtask 2, we fine-tune DeBERTaV3 for classification without relying on the results from Subtask 1, and we observe that early stopping can effectively prevent model overfitting, which performs well in Subtask 2. In addition, we did not use any ensemble strategies. Ultimately, we achieved the 10th place in Subtask 1 and the 2nd place in Subtask 2.</abstract>
<identifier type="citekey">zhao-etal-2023-hw</identifier>
<identifier type="doi">10.18653/v1/2023.semeval-1.221</identifier>
<location>
<url>https://aclanthology.org/2023.semeval-1.221</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>1603</start>
<end>1608</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HW-TSC at SemEval-2023 Task 7: Exploring the Natural Language Inference Capabilities of ChatGPT and Pre-trained Language Model for Clinical Trial
%A Zhao, Xiaofeng
%A Zhang, Min
%A Ma, Miaomiao
%A Su, Chang
%A Liu, Yilun
%A Wang, Minghan
%A Qiao, Xiaosong
%A Guo, Jiaxin
%A Li, Yinglu
%A Ma, Wenbing
%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 zhao-etal-2023-hw
%X In this paper, we describe the multi strategy system for SemEval-2022 Task 7, This task aims to determine whether a given statement is supported by one or two Clinical Trial reports, and to identify evidence that supports the statement. This is a task that requires high natural language inference capabilities. In Subtask 1, we compare our strategy based on prompt learning and ChatGPT with a baseline constructed using BERT in zero-shot setting, and validate the effectiveness of our strategy. In Subtask 2, we fine-tune DeBERTaV3 for classification without relying on the results from Subtask 1, and we observe that early stopping can effectively prevent model overfitting, which performs well in Subtask 2. In addition, we did not use any ensemble strategies. Ultimately, we achieved the 10th place in Subtask 1 and the 2nd place in Subtask 2.
%R 10.18653/v1/2023.semeval-1.221
%U https://aclanthology.org/2023.semeval-1.221
%U https://doi.org/10.18653/v1/2023.semeval-1.221
%P 1603-1608
Markdown (Informal)
[HW-TSC at SemEval-2023 Task 7: Exploring the Natural Language Inference Capabilities of ChatGPT and Pre-trained Language Model for Clinical Trial](https://aclanthology.org/2023.semeval-1.221) (Zhao et al., SemEval 2023)
ACL
- Xiaofeng Zhao, Min Zhang, Miaomiao Ma, Chang Su, Yilun Liu, Minghan Wang, Xiaosong Qiao, Jiaxin Guo, Yinglu Li, and Wenbing Ma. 2023. HW-TSC at SemEval-2023 Task 7: Exploring the Natural Language Inference Capabilities of ChatGPT and Pre-trained Language Model for Clinical Trial. In Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023), pages 1603–1608, Toronto, Canada. Association for Computational Linguistics.