• Shravani Soma
• Kacharla Navya
• K. Manilekha

A vast quantity of text data is generated on the internet, be it social media articles, news articles, etc. Manual creation of summaries is time-consuming, and therefore a need for automatic text summaries has arisen. Abstractive Text Summarization is the task of generating a short and concise summary that captures the salient ideas of the source text. The generated summaries potentially contain new phrases and sentences that may not appear in the source text. In this work, we model abstractive text summarization using Attentional Encoder Decoder using transformers, and show that they achieve state-of-the-art performance on two different corpora. We studied on several novel models that address critical problems in summarization that are not adequately modelled by the basic architecture, such as modelling key-words, capturing the hierarchy of sentence-to word structure, and emitting words that are rare or unseen at training time. Our work shows that our proposed model contribute to further improvement in performance. In future, we will also try to propose a new dataset consisting of multisentence summaries, and establish performance benchmarks for further research.

TEXT SUMMARIZATION

"TEXT SUMMARIZATION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 6, page no.e657-e663, June-2022, Available :http://www.jetir.org/papers/JETIR2206477.pdf

"TEXT SUMMARIZATION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 6, page no. ppe657-e663, June-2022, Available at : http://www.jetir.org/papers/JETIR2206477.pdf