Indian Journal of Science and Technology
DOI: 10.17485/IJST/v16iSP2.5429
Year: 2023, Volume: 16, Issue: Special Issue 2, Pages: 22-29
Original Article
Pritom Jyoti Goutom1*, Nomi Baruah2
1Center for computer Science and Application, Dibrugarh University, Dibrugarh, Assam, India
2Department of Computer Science and Engineering, DUIET, Dibrugarh University, Dibrugarh, Assam, India
*Corresponding Author
Email: [email protected]
Received Date:23 March 2023, Accepted Date:26 June 2023, Published Date:02 November 2023
This study discusses an approach for abstractive text summarization in the Assamese language. Objective: The main objective of this paper is to develop a novel approach for abstractive text summarization in Assamese that efficiently condenses large information while keeping its core meaning. Methods: We utilise a sequence-to-sequence Recurrent Neural Network [RNN] model with an encoder-decoder architecture in this paper. In this study, we use a Bi-LSTM on the encoder side, an attention mechanism, a softmax layer on the decoder side, and Assamese news items obtained from renowned daily newspapers in Assam. Findings: The results show that the suggested model is effective, with a train loss of 0.008 and assessment scores based on ROUGE-1, ROUGE-2, and ROUGE-L criteria. Novelty: The novelty lies in filling the aforementioned gap by proposing and implementing an abstractive text summarization approach for the Assamese language. Improve Assamese text summarization approaches by applying the presented strategy to news items.
Keywords: Abstractive, NLP, RNN, Seq2Seq, Text summarization
© 2023 Goutom & Baruah. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Published By Indian Society for Education and Environment (iSee)
Subscribe now for latest articles and news.