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.
CITATION STYLE
Quoc, V. N., Thanh, H. L., & Minh, T. L. (2020). Abstractive Text Summarization Using LSTMs with Rich Features. In Communications in Computer and Information Science (Vol. 1215 CCIS, pp. 28–40). Springer. https://doi.org/10.1007/978-981-15-6168-9_3
Mendeley helps you to discover research relevant for your work.