Data Summerization and Voice Assistant
Laxman Singh1, Ram Kumar Sharma2, Nikhil Saini3, Mrtyunjy Singh4
1Prof Mr. Laxman Singh, Assistant Professor, Department of Computer Science, ABES Institute of Technology, Ghaziabad (Uttar Pradesh), India.
2Ram Kumar Sharma, Student, Department of Computer Science, ABES Institute of Technology, Ghaziabad (Uttar Pradesh), India.
3Nikhil Saini, Student, Department of Computer Science, ABES Institute of Technology, Ghaziabad (Uttar Pradesh), India.
4Mrtyunjy Singh, Student, Department of Computer Science, ABES Institute of Technology, Ghaziabad (Uttar Pradesh), India.
Manuscript received on 28 August 2023 | Revised Manuscript received on 05 September 2023 | Manuscript Accepted on 15 September 2023 | Manuscript published on 30 September 2023 | PP: 21-24 | Volume-12 Issue-10, September 2023 | Retrieval Number: 100.1/ijitee.C979613030224 | DOI: 10.35940/ijitee.C9796.09121023
Open Access | Editorial and Publishing Policies | Cite | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: This project focuses on data collection and writing, aiming to develop a framework for efficiently summarizing extensive knowledge available on the Internet. The proposed framework leverages morphological content and semantic information to sift through the vast amount of data online. The current information landscape is overwhelming, making it challenging for individuals to quickly extract pertinent details. The sheer volume of data on the Internet poses difficulties in searching for and assimilating relevant information from diverse sources. The solution lies in the development of an automatic writing system to address these challenges effectively. Summary summarization, a crucial aspect of this framework, involves identifying and condensing the most essential and valuable information from a given dataset. The goal is to create a concise version that retains the original purpose of the data entry. The significance of this approach becomes apparent in the face of the daunting task of making sense of big data, streamlining the process and facilitating efficient extraction of meaningful insights.
Keywords: Natural Language Processing (NLP), SBERT, Transformer, Hugging face, Tokens, Machine Learning, Summarization.
Scope of the Article: Computer Science and Applications