NORMA eResearch @NCI Library

Business Meeting Summary Generation using Natural Language Processing (NLP)

Prasad, Srishti Subhash Chandra (2022) Business Meeting Summary Generation using Natural Language Processing (NLP). Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (2MB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (2MB) | Preview


Text summarization is a challenging task in the domain of NLP (Natural Language Processing). In this modern period, where enormous amounts of data are available online, it is challenging to provide a better model for extracting information efficiently and quickly. Manually extracting the summary of a huge written document is quite challenging for humans. Researchers used to focus mostly on extractive ways, but there's been a steady shift in the stream of research toward abstractive ways as it is more difficult to implement. Meeting summaries compress the most important things spoken at a meeting while maintaining the meeting's original meaning, as reading through the complete transcripts is time consuming and costly to the company. The dataset was taken from the ICSI corpus which contains 75 meetings, lasting around 72 hours. The meetings have an average of 6 attendees, and each transcript contains an average of 1000 lines to process for summarization. The meeting summarization is achieved by combining both the abstractive and extractive approaches: the extractive approach incorporates feature extraction based on TextRank or graph-based ranking algorithm and word frequency, while the abstractive approach uses deep learning technique which comprises of RNN, LSTM with an attention mechanism model . The performance or summary evaluation was calculated using ROUGE and human evaluation.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
H Social Sciences > HD Industries. Land use. Labor > HD28 Management. Industrial Management > Business Communication
P Language and Literature > P Philology. Linguistics > Computational linguistics. Natural language processing
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Tamara Malone
Date Deposited: 28 Feb 2023 17:50
Last Modified: 01 Mar 2023 17:45

Actions (login required)

View Item View Item