SubmissionNumber#=%=#31
FinalPaperTitle#=%=#SCaLAR NITK at SemEval-2024 Task 5: Towards Unsupervised Question Answering system with Multi-level Summarization for Legal Text
ShortPaperTitle#=%=#
NumberOfPages#=%=#7
CopyrightSigned#=%=#M Manvith Prabhu
JobTitle#==#
Organization#==#National Institute of Technology, Karnataka - Surathkal,
NH-66, Srinivasnagar, Mangalore
Karnataka, India.
Pincode: 575025
Abstract#==#This paper summarizes Team SCaLAR's work on SemEval-2024 Task 5: Legal Argument Reasoning in Civil Procedure. To address this Binary Classification task, which was daunting due to the complexity of the Legal Texts involved, we propose a simple yet novel similarity and distance-based unsupervised approach to generate labels. Further, we explore the Multi-level fusion of Legal-Bert embeddings using ensemble features, including CNN, GRU, and LSTM. To address the lengthy nature of Legal explanation in the dataset, we introduce T5-based segment-wise summarization, which successfully retained crucial information, enhancing the model's performance. Our unsupervised system witnessed a 20-point increase in macro F1-score on the development set and a 10-point increase on the test set, which is promising given its uncomplicated architecture.
Author{1}{Firstname}#=%=#M Manvith
Author{1}{Lastname}#=%=#Prabhu
Author{1}{Username}#=%=#manvith_prabhu
Author{1}{Email}#=%=#manvithprabhu.211ec228@nitk.edu.in
Author{1}{Affiliation}#=%=#National Institute of Technology - Karnataka at Surathkal
Author{2}{Firstname}#=%=#Haricharana
Author{2}{Lastname}#=%=#Srinivasa
Author{2}{Email}#=%=#sharicharana.211ch024@nitk.edu.in
Author{2}{Affiliation}#=%=#National Institute of Technology - Karnataka at Surathkal
Author{3}{Firstname}#=%=#Anand Kumar
Author{3}{Lastname}#=%=#M
Author{3}{Username}#=%=#anandkumar
Author{3}{Email}#=%=#m_anandkumar@nitk.edu.in
Author{3}{Affiliation}#=%=#National Institute of Technology Karnataka

==========
èéáğö