@inproceedings{nath-samin-2024-bd,
title = "{BD}-{NLP} at {S}em{E}val-2024 Task 2: Investigating Generative and Discriminative Models for Clinical Inference with Knowledge Augmentation",
author = "Nath, Shantanu and
Samin, Ahnaf Mozib",
editor = {Ojha, Atul Kr. and
Do{\u{g}}ru{\"o}z, A. Seza and
Tayyar Madabushi, Harish and
Da San Martino, Giovanni and
Rosenthal, Sara and
Ros{\'a}, Aiala},
booktitle = "Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.semeval-1.188",
doi = "10.18653/v1/2024.semeval-1.188",
pages = "1302--1308",
abstract = "Healthcare professionals rely on evidence from clinical trial records (CTRs) to devise treatment plans. However, the increasing quantity of CTRs poses challenges in efficiently assimilating the latest evidence to provide personalized evidence-based care. In this paper, we present our solution to the SemEval- 2024 Task 2 titled {``}Safe Biomedical Natural Language Inference for Clinical Trials{''}. Given a statement and one/two CTRs as inputs, the task is to determine whether or not the statement entails or contradicts the CTRs. We explore both generative and discriminative large language models (LLM) to investigate their performance for clinical inference. Moreover, we contrast the general-purpose LLMs with the ones specifically tailored for the clinical domain to study the potential advantage in mitigating distributional shifts. Furthermore, the benefit of augmenting additional knowledge within the prompt/statement is examined in this work. Our empirical study suggests that DeBERTa-lg, a discriminative general-purpose natural language inference model, obtains the highest F1 score of 0.77 on the test set, securing the fourth rank on the leaderboard. Intriguingly, the augmentation of knowledge yields subpar results across most cases.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nath-samin-2024-bd">
<titleInfo>
<title>BD-NLP at SemEval-2024 Task 2: Investigating Generative and Discriminative Models for Clinical Inference with Knowledge Augmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shantanu</namePart>
<namePart type="family">Nath</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahnaf</namePart>
<namePart type="given">Mozib</namePart>
<namePart type="family">Samin</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 18th International Workshop on Semantic Evaluation (SemEval-2024)</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">Harish</namePart>
<namePart type="family">Tayyar Madabushi</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">Sara</namePart>
<namePart type="family">Rosenthal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aiala</namePart>
<namePart type="family">Rosá</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>Healthcare professionals rely on evidence from clinical trial records (CTRs) to devise treatment plans. However, the increasing quantity of CTRs poses challenges in efficiently assimilating the latest evidence to provide personalized evidence-based care. In this paper, we present our solution to the SemEval- 2024 Task 2 titled “Safe Biomedical Natural Language Inference for Clinical Trials”. Given a statement and one/two CTRs as inputs, the task is to determine whether or not the statement entails or contradicts the CTRs. We explore both generative and discriminative large language models (LLM) to investigate their performance for clinical inference. Moreover, we contrast the general-purpose LLMs with the ones specifically tailored for the clinical domain to study the potential advantage in mitigating distributional shifts. Furthermore, the benefit of augmenting additional knowledge within the prompt/statement is examined in this work. Our empirical study suggests that DeBERTa-lg, a discriminative general-purpose natural language inference model, obtains the highest F1 score of 0.77 on the test set, securing the fourth rank on the leaderboard. Intriguingly, the augmentation of knowledge yields subpar results across most cases.</abstract>
<identifier type="citekey">nath-samin-2024-bd</identifier>
<identifier type="doi">10.18653/v1/2024.semeval-1.188</identifier>
<location>
<url>https://aclanthology.org/2024.semeval-1.188</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>1302</start>
<end>1308</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BD-NLP at SemEval-2024 Task 2: Investigating Generative and Discriminative Models for Clinical Inference with Knowledge Augmentation
%A Nath, Shantanu
%A Samin, Ahnaf Mozib
%Y Ojha, Atul Kr.
%Y Doğruöz, A. Seza
%Y Tayyar Madabushi, Harish
%Y Da San Martino, Giovanni
%Y Rosenthal, Sara
%Y Rosá, Aiala
%S Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F nath-samin-2024-bd
%X Healthcare professionals rely on evidence from clinical trial records (CTRs) to devise treatment plans. However, the increasing quantity of CTRs poses challenges in efficiently assimilating the latest evidence to provide personalized evidence-based care. In this paper, we present our solution to the SemEval- 2024 Task 2 titled “Safe Biomedical Natural Language Inference for Clinical Trials”. Given a statement and one/two CTRs as inputs, the task is to determine whether or not the statement entails or contradicts the CTRs. We explore both generative and discriminative large language models (LLM) to investigate their performance for clinical inference. Moreover, we contrast the general-purpose LLMs with the ones specifically tailored for the clinical domain to study the potential advantage in mitigating distributional shifts. Furthermore, the benefit of augmenting additional knowledge within the prompt/statement is examined in this work. Our empirical study suggests that DeBERTa-lg, a discriminative general-purpose natural language inference model, obtains the highest F1 score of 0.77 on the test set, securing the fourth rank on the leaderboard. Intriguingly, the augmentation of knowledge yields subpar results across most cases.
%R 10.18653/v1/2024.semeval-1.188
%U https://aclanthology.org/2024.semeval-1.188
%U https://doi.org/10.18653/v1/2024.semeval-1.188
%P 1302-1308
Markdown (Informal)
[BD-NLP at SemEval-2024 Task 2: Investigating Generative and Discriminative Models for Clinical Inference with Knowledge Augmentation](https://aclanthology.org/2024.semeval-1.188) (Nath & Samin, SemEval 2024)
ACL