Neural Extractive Text Summarization with Syntactic Compression

Abstract

Recent neural network approaches to summarization are largely either selection-based extraction or generation-based abstraction. In this work, we present a neural model for single-document summarization based on joint extraction and syntactic compression. Our model chooses sentences from the document, identifies possible compressions based on constituency parses, and scores those compressions with a neural model to produce the final summary. For learning, we construct oracle extractive-compressive summaries, then learn both of our components jointly with this supervision. Experimental results on the CNN/Daily Mail and New York Times datasets show that our model achieves strong performance (comparable to state-of-the-art systems) as evaluated by ROUGE. Moreover, our approach outperforms an off-the-shelf compression module, and human and manual evaluation shows that our model's output generally remains grammatical.

14 pages, EMNLP 2019

References in corpus (4)

• A Deep Reinforced Model for Abstractive Summarization
• SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documents
• Faithful to the Original: Fact Aware Neural Abstractive Summarization
• A Sentence Compression Based Framework to Query-Focused Multi-Document Summarization

Cited by in corpus (7)

• HIBERT: Document Level Pre-training of Hierarchical Bidirectional Transformers for Document Summarization
• Heterogeneous Graph Neural Networks for Extractive Document Summarization
• Probabilistic Model of Narratives Over Topical Trends in Social Media: A Discrete Time Model
• Summary Level Training of Sentence Rewriting for Abstractive Summarization
• Modelling Latent Skills for Multitask Language Generation
• SciSummPip: An Unsupervised Scientific Paper Summarization Pipeline
• Reference and Document Aware Semantic Evaluation Methods for Korean Language Summarization