Abstractive Summarization with NLP Makes Easier to Memorize
Bhumika1, V. Srikanth2
1Bhumika, Assistant Professor (Computer Applications) in Dr. Y.S. Parmar Govt. PG College Nahan, District Sirmaur,
2Dr.V.Srikanth, Associate Professor in Department of AIT IBM CSE Chandigarh University, India.
Manuscript received on January 05, 2020. | Revised Manuscript received on January 25, 2020. | Manuscript published on January 30, 2020. | PP: 4939-4944 | Volume-8 Issue-5, January 2020. | Retrieval Number: E6085018520/2020©BEIESP | DOI: 10.35940/ijrte.E6085.018520
Open Access | Ethics and 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: Summarization is used to extract most relevant content from a huge content. It can be extractive and abstractive. But different people may have different scope of relevance in different area. Content can be in the form of opinions, news, judgments and ideas etc. Extractive Summarization extracts most focusing content without any change in the original content. Abstractive summarization is a knowledgebase extraction with some modification in original content. In this paper first we discuss various algorithm for abstractive summarization then on the basis of merits of various algorithm discussed in conclusions, we propose a new algorithm for abstractive summarization with the help of NLP to generate shortcuts from the content that make easier to memorize the content. Challenges in Abstractive summarization, Repetition or duplicity of the conten, Arrangement of words, Different people have different meaning for the same content, Number of times a content repeated, Different people have different interest, Nosiness in content, Information diversity Methods for Abstractive summarization: 1. integer linear programming-based summarization framework . 2. Improved Semantic Graph Approach . 3. novel speech act-guided summarization approach . 4. Neural Abstractive Summarization with Diverse Decoding(NASDD) . 5. Supervised and unsupervised approach . 6. Neural network based representation . 7. Integer linear optimization . 8. Maximum L∞-norm and minimum entropy regularization . 9. Opizer-E and Opizer-A  10. LSTM-CNN based ATSDL model . 11. novel concept-level approach .
Keywords: Abstractive Summarization, Diverse Decoding , Opinion Summarization .
Scope of the Article: Smart Learning and Innovative Education Systems.