Classify or Select: Neural Architectures for Extractive Document Summarization
This work addresses the problem of automated document summarization for NLP applications, offering interpretable models with competitive performance, though it is incremental in advancing existing neural methods.
The paper tackles extractive document summarization by proposing two RNN-based architectures, Classifier and Selector, which jointly model salience and redundancy to generate summaries, achieving or surpassing state-of-the-art supervised models on two corpora.
We present two novel and contrasting Recurrent Neural Network (RNN) based architectures for extractive summarization of documents. The Classifier based architecture sequentially accepts or rejects each sentence in the original document order for its membership in the final summary. The Selector architecture, on the other hand, is free to pick one sentence at a time in any arbitrary order to piece together the summary. Our models under both architectures jointly capture the notions of salience and redundancy of sentences. In addition, these models have the advantage of being very interpretable, since they allow visualization of their predictions broken up by abstract features such as information content, salience and redundancy. We show that our models reach or outperform state-of-the-art supervised models on two different corpora. We also recommend the conditions under which one architecture is superior to the other based on experimental evidence.