Abstractive summarization is the technique of generating a summary of a text from its main ideas, not by copying verbatim most salient sentences from text. There have been many different algorithms and methods for performing this task including the use of RNNs or the newer networks: Transformers.
Abstractive Text Summarization using Transformer
-
Implementation of the state of the art Transformer Model from "Attention is all you need", Vaswani et. al. https://arxiv.org/abs/1706.03762
-
Inshorts Dataset: https://www.kaggle.com/shashichander009/inshorts-news-data