SubmissionNumber#=%=#19
FinalPaperTitle#=%=#RGAT at SemEval-2024 Task 2: Biomedical Natural Language Inference using Graph Attention Network
ShortPaperTitle#=%=#
NumberOfPages#=%=#7
CopyrightSigned#=%=#Abir Chakraborty
JobTitle#==#
Organization#==#Microsoft Corporation, One Microsoft Way, Redmond, WA 98052
Abstract#==#In this work, we (team RGAT) describe our approaches for the SemEval 2024 Task 2: Safe Biomedical Natural Language Inference for Clinical Trials (NLI4CT). The objective of this task is multi-evidence natural language inference based on different sections of clinical trial reports. We have explored various approaches, (a) dependency tree of the input query as additional features in a Graph Attention Network (GAT) along with the token and parts-of-speech features, (b) sequence-to-sequence approach using various models and synthetic data and finally, (c) in-context learning using large language models (LLMs) like GPT-4. Amongs these three approaches the best result is obtained from the LLM with 0.76 F1-score (the highest being 0.78), 0.86 in faithfulness and 0.74 in consistence.
Author{1}{Firstname}#=%=#Abir
Author{1}{Lastname}#=%=#Chakraborty
Author{1}{Username}#=%=#abirnlp
Author{1}{Email}#=%=#abir.chakraborty@gmail.com
Author{1}{Affiliation}#=%=#Microsoft

==========
èéáğö