Print Email Facebook Twitter Evaluating the effectiveness of large language models in meeting summarization with transcript segmentation techniques Title Evaluating the effectiveness of large language models in meeting summarization with transcript segmentation techniques: How well does gpt-3.5-turbo perform on meeting summarization with topic and context-length window segmentation? Author Sándor, Kristóf (TU Delft Electrical Engineering, Mathematics and Computer Science) Contributor Tarvirdians, M. (mentor) Jonker, C.M. (mentor) Molenaar, M.L. (graduation committee) Degree granting institution Delft University of Technology Programme Computer Science and Engineering Project CSE3000 Research Project Date 2023-07-03 Abstract Large Language Models (LLM) have brought significant performance increase on many Natural Language Processing tasks. However LLMs have not been tested for meeting summarization. This research paper examines the effectiveness of the gpt-3.5-turbo model on the meeting summarization domain. However due to input length limitations, it cannot be applied directly to this task. Thus the paper investigates two segmentation methods: a simple context-length window approach and topic segmentation using Latent Dirichlet Allocation (LDA). The context-length window approach's performance is close to the Pointer Generator framework. The topic segmentation gives worse results. Overall gpt-3.5-turbo performs worse with both approaches than state-of-the-art models which use a transformer architecture adapted for long documents. Subject Natural Language Processing (NLP)meeting summarizationmeeting transcriptsummarizationtext summarizationdialogue summarizationLarge Language ModelsGPT-3 To reference this document use: http://resolver.tudelft.nl/uuid:e2ce9fbb-435c-446e-9327-95f26d0336d5 Part of collection Student theses Document type bachelor thesis Rights © 2023 Kristóf Sándor Files PDF KA_S_ndor_CSE3000_Final_P ... er_11_.pdf 124.22 KB Close viewer /islandora/object/uuid:e2ce9fbb-435c-446e-9327-95f26d0336d5/datastream/OBJ/view