@inproceedings{kanakarajan-sankarasubbu-2023-saama,
title = "Saama {AI} Research at {S}em{E}val-2023 Task 7: Exploring the Capabilities of Flan-T5 for Multi-evidence Natural Language Inference in Clinical Trial Data",
author = "Kanakarajan, Kamal Raj and
Sankarasubbu, Malaikannan",
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-1.137/",
doi = "10.18653/v1/2023.semeval-1.137",
pages = "995--1003",
abstract = "The goal of the NLI4CT task is to build a Natural Language Inference system for Clinical Trial Reports that will be used for evidence interpretation and retrieval. Large Language models have demonstrated state-of-the-art performance in various natural language processing tasks across multiple domains. We suggest using an instruction-finetuned Large Language Models (LLMs) to take on this particular task in light of these developments. We have evaluated the publicly available LLMs under zeroshot setting, and finetuned the best performing Flan-T5 model for this task. On the leaderboard, our system ranked second, with an F1 Score of 0.834 on the official test set."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kanakarajan-sankarasubbu-2023-saama">
<titleInfo>
<title>Saama AI Research at SemEval-2023 Task 7: Exploring the Capabilities of Flan-T5 for Multi-evidence Natural Language Inference in Clinical Trial Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kamal</namePart>
<namePart type="given">Raj</namePart>
<namePart type="family">Kanakarajan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malaikannan</namePart>
<namePart type="family">Sankarasubbu</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>The goal of the NLI4CT task is to build a Natural Language Inference system for Clinical Trial Reports that will be used for evidence interpretation and retrieval. Large Language models have demonstrated state-of-the-art performance in various natural language processing tasks across multiple domains. We suggest using an instruction-finetuned Large Language Models (LLMs) to take on this particular task in light of these developments. We have evaluated the publicly available LLMs under zeroshot setting, and finetuned the best performing Flan-T5 model for this task. On the leaderboard, our system ranked second, with an F1 Score of 0.834 on the official test set.</abstract>
<identifier type="citekey">kanakarajan-sankarasubbu-2023-saama</identifier>
<identifier type="doi">10.18653/v1/2023.semeval-1.137</identifier>
<location>
<url>https://aclanthology.org/2023.semeval-1.137/</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>995</start>
<end>1003</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Saama AI Research at SemEval-2023 Task 7: Exploring the Capabilities of Flan-T5 for Multi-evidence Natural Language Inference in Clinical Trial Data
%A Kanakarajan, Kamal Raj
%A Sankarasubbu, Malaikannan
%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 kanakarajan-sankarasubbu-2023-saama
%X The goal of the NLI4CT task is to build a Natural Language Inference system for Clinical Trial Reports that will be used for evidence interpretation and retrieval. Large Language models have demonstrated state-of-the-art performance in various natural language processing tasks across multiple domains. We suggest using an instruction-finetuned Large Language Models (LLMs) to take on this particular task in light of these developments. We have evaluated the publicly available LLMs under zeroshot setting, and finetuned the best performing Flan-T5 model for this task. On the leaderboard, our system ranked second, with an F1 Score of 0.834 on the official test set.
%R 10.18653/v1/2023.semeval-1.137
%U https://aclanthology.org/2023.semeval-1.137/
%U https://doi.org/10.18653/v1/2023.semeval-1.137
%P 995-1003
Markdown (Informal)
[Saama AI Research at SemEval-2023 Task 7: Exploring the Capabilities of Flan-T5 for Multi-evidence Natural Language Inference in Clinical Trial Data](https://aclanthology.org/2023.semeval-1.137/) (Kanakarajan & Sankarasubbu, SemEval 2023)
ACL