An LSTM based seq2seq (Encoder-decoder) language model to predict summaries for natural language data. Wikihow data was used to develop the model.
Text summarizing can be used to automatically create short summaries of longer text. In the age of the internet, we are constantly bombarded with a lot of information where you can lose the overview quickly. Extractive and abstractive text summarization are of great help to come up with short summaries of the given text. The extractive approach focuses on the relevant sentences in the document according to some certain criteria. The abstractive approach tries to increase the coherence among the sentences through the elimination of redundancies and clarification of the content of the sentences. This paper describes the modelling of an LSTM for extractive text summarization.
Laura Oberscheid and Gururaj Desai
https://www.analyticsvidhya.com/blog/2019/06/comprehensive-guide-text-summarization-using-deep-learning-python/ article was followed to implement this.