Classify or Select: Neural Architectures for Extractive Document Summarization

Abstract

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.

arXiv admin note: text overlap with arXiv:1611.04230

References in corpus (3)

• ADADELTA: An Adaptive Learning Rate Method
• Neural Summarization by Extracting Sentences and Words
• AttSum: Joint Learning of Focusing and Summarization with Neural Attention

Cited by in corpus (12)

• A Hierarchical Structured Self-Attentive Model for Extractive Document Summarization (HSSAS)
• Investigating Entropy for Extractive Document Summarization
• A Unified Model for Extractive and Abstractive Summarization using Inconsistency Loss
• On Extractive and Abstractive Neural Document Summarization with Transformer Language Models
• A Condense-then-Select Strategy for Text Summarization
• Multi-Reference Training with Pseudo-References for Neural Translation and Text Generation
• Learning Sentence Embeddings for Coherence Modelling and Beyond
• Reference and Document Aware Semantic Evaluation Methods for Korean Language Summarization
• Learning to Summarize Long Texts with Memory Compression and Transfer
• Data Augmentation for Abstractive Query-Focused Multi-Document Summarization
• Learning to Summarize Passages: Mining Passage-Summary Pairs from Wikipedia Revision Histories
• Improving Abstractive Text Summarization with History Aggregation