@inproceedings{alameldin-williamson-2023-clemson,
title = "Clemson {NLP} at {S}em{E}val-2023 Task 7: Applying {G}ator{T}ron to Multi-Evidence Clinical {NLI}",
author = "Alameldin, Ahamed and
Williamson, Ashton",
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-1.220",
doi = "10.18653/v1/2023.semeval-1.220",
pages = "1598--1602",
abstract = "This paper presents our system descriptions for SemEval 2023-Task 7: Multi-evidence Natural Language Inference for Clinical Trial Data sub-tasks one and two. Provided with a collection of Clinical Trial Reports (CTRs) and corresponding expert-annotated claim statements, sub-task one involves determining an inferential relationship between the statement and CTR premise: contradiction or entailment. Sub-task two involves retrieving evidence from the CTR which is necessary to determine the entailment in sub-task one. For sub-task two we employ a recent transformer-based language model pretrained on biomedical literature, which we domain-adapt on a set of clinical trial reports. For sub-task one, we take an ensemble approach in which we leverage the evidence retrieval model from sub-task two to extract relevant sections, which are then passed to a second model of equivalent architecture to determine entailment. Our system achieves a ranking of seventh on sub-task one with an F1-score of 0.705 and sixth on sub-task two with an F1-score of 0.806. In addition, we find that the high rate of success of language models on this dataset may be partially attributable to the existence of annotation artifacts.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alameldin-williamson-2023-clemson">
<titleInfo>
<title>Clemson NLP at SemEval-2023 Task 7: Applying GatorTron to Multi-Evidence Clinical NLI</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ahamed</namePart>
<namePart type="family">Alameldin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashton</namePart>
<namePart type="family">Williamson</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>This paper presents our system descriptions for SemEval 2023-Task 7: Multi-evidence Natural Language Inference for Clinical Trial Data sub-tasks one and two. Provided with a collection of Clinical Trial Reports (CTRs) and corresponding expert-annotated claim statements, sub-task one involves determining an inferential relationship between the statement and CTR premise: contradiction or entailment. Sub-task two involves retrieving evidence from the CTR which is necessary to determine the entailment in sub-task one. For sub-task two we employ a recent transformer-based language model pretrained on biomedical literature, which we domain-adapt on a set of clinical trial reports. For sub-task one, we take an ensemble approach in which we leverage the evidence retrieval model from sub-task two to extract relevant sections, which are then passed to a second model of equivalent architecture to determine entailment. Our system achieves a ranking of seventh on sub-task one with an F1-score of 0.705 and sixth on sub-task two with an F1-score of 0.806. In addition, we find that the high rate of success of language models on this dataset may be partially attributable to the existence of annotation artifacts.</abstract>
<identifier type="citekey">alameldin-williamson-2023-clemson</identifier>
<identifier type="doi">10.18653/v1/2023.semeval-1.220</identifier>
<location>
<url>https://aclanthology.org/2023.semeval-1.220</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>1598</start>
<end>1602</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Clemson NLP at SemEval-2023 Task 7: Applying GatorTron to Multi-Evidence Clinical NLI
%A Alameldin, Ahamed
%A Williamson, Ashton
%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 alameldin-williamson-2023-clemson
%X This paper presents our system descriptions for SemEval 2023-Task 7: Multi-evidence Natural Language Inference for Clinical Trial Data sub-tasks one and two. Provided with a collection of Clinical Trial Reports (CTRs) and corresponding expert-annotated claim statements, sub-task one involves determining an inferential relationship between the statement and CTR premise: contradiction or entailment. Sub-task two involves retrieving evidence from the CTR which is necessary to determine the entailment in sub-task one. For sub-task two we employ a recent transformer-based language model pretrained on biomedical literature, which we domain-adapt on a set of clinical trial reports. For sub-task one, we take an ensemble approach in which we leverage the evidence retrieval model from sub-task two to extract relevant sections, which are then passed to a second model of equivalent architecture to determine entailment. Our system achieves a ranking of seventh on sub-task one with an F1-score of 0.705 and sixth on sub-task two with an F1-score of 0.806. In addition, we find that the high rate of success of language models on this dataset may be partially attributable to the existence of annotation artifacts.
%R 10.18653/v1/2023.semeval-1.220
%U https://aclanthology.org/2023.semeval-1.220
%U https://doi.org/10.18653/v1/2023.semeval-1.220
%P 1598-1602
Markdown (Informal)
[Clemson NLP at SemEval-2023 Task 7: Applying GatorTron to Multi-Evidence Clinical NLI](https://aclanthology.org/2023.semeval-1.220) (Alameldin & Williamson, SemEval 2023)
ACL