A Pointer Generator Network Model to Automatic Text Summarization and Headline Generation
Anubha Agrawal1, Sakshi Saraswat2, Hira Javed3
1Anubha Agrawal, Department of Computer Engineering, Aligarh Muslim University, Aligarh (U.P), India.
2Sakshi Saraswat, Department of Computer Engineering, Aligarh Muslim University, Aligarh (U.P), India.
3Hira Javed, Department of Computer Engineering, Aligarh Muslim University, Aligarh (U.P), India.
Manuscript received on 27 August 2019 | Revised Manuscript received on 03 September 2019 | Manuscript Published on 14 September 2019 | PP: 447-451 | Volume-8 Issue-5S3, July 2019 | Retrieval Number: E10940785S319/19©BEIESP | DOI: 10.35940/ijeat.E1094.0785S319
Open Access | Editorial and Publishing Policies | Cite | Mendeley | 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: In a world where information is growing rapidly every single day, we need tools to generate summary and headlines from text which is accurate as well as short and precise. In this paper, we have described a method for generating headlines from article. This is done by using hybrid pointer-generator network with attention distribution and coverage mechanism on article which generates abstractive summarization followed by the application of encoder-decoder recurrent neural network with LSTM unit to generate headlines from the summary. Hybrid pointer generator model helps in removing inaccuracy as well as repetitions. We have used CNN / Daily Mail as our dataset.
Keywords: LSTM Encoder Decoder Model, Natural Language Processing, Pointer Generator Network and Coverage Mechanism, Text Summarization.
Scope of the Article: Adaptive Networking Applications