Text summarization using deep learning – LSTM approach

Abstract

Text summarization is a process of extracting the context of a large document and summarize it into a smaller paragraph or a few sentences. Machine learning and deep learning, as we know, have started ruling over almost every field in the computing industry and so, has revolutionized the process of text summarization too. Automatic text summarization is an advancing realm of the natural language processing research in which concise textual summaries are generated from lengthy input documents. Neural network models have been provided a new feasible approach for abstractive text summarization. Abstractive means generating new sentences from the original text which might not be present in the original text. These neural network models have two defects: They are likely to reproduce factual details inaccurately and they tend to repeat themselves. Extensive research has been carried out on how automatic summarization can be prosecuted through various extractive and abstractive techniques. It is also used in many bigger project implementations of classification of documents or in search engines. This presentation presents a method of achieving text summaries accurately using deep learning methods, mainly focusing on LSTMs(Long Short Term Memory) for prediction accuracy.