Abstractive Text Summarization Using LSTMs with Rich Features

Abstract

Abstractive text summarization using sequence-to-sequence networks have been successful for short text. However, these models have shown their limitations in summarizing long text as they forget sentences in long distance. We propose an abstractive summarization model using rich features to overcome this weakness. The proposed system has been tested with two datasets: an English dataset (CNN/Daily Mail) and a Vietnamese dataset (Baomoi). Experimental results show that our model significantly outperforms recently proposed models on both datasets.