Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond
This work addresses the problem of generating concise summaries for natural language processing applications, with incremental improvements over existing methods.
The authors tackled abstractive text summarization by modeling it with Attentional Encoder-Decoder RNNs, achieving state-of-the-art performance on two corpora and proposing novel models to address issues like keyword modeling and rare word emission.
In this work, we model abstractive text summarization using Attentional Encoder-Decoder Recurrent Neural Networks, and show that they achieve state-of-the-art performance on two different corpora. We propose several novel models that address critical problems in summarization that are not adequately modeled by the basic architecture, such as modeling key-words, capturing the hierarchy of sentence-to-word structure, and emitting words that are rare or unseen at training time. Our work shows that many of our proposed models contribute to further improvement in performance. We also propose a new dataset consisting of multi-sentence summaries, and establish performance benchmarks for further research.