Neural Summarization by Extracting Sentences and Words

Abstract

Traditional approaches to extractive summarization rely heavily on human-engineered features. In this work we propose a data-driven approach based on neural networks and continuous sentence features. We develop a general framework for single-document summarization composed of a hierarchical document encoder and an attention-based extractor. This architecture allows us to develop different classes of summarization models which can extract sentences or words. We train our models on large scale corpora containing hundreds of thousands of document-summary pairs. Experimental results on two summarization datasets demonstrate that our models obtain results comparable to the state of the art without any access to linguistic annotation.

arXiv commentACL2016 conference paper with appendix

References in corpus (10)

• Adam: A Method for Stochastic Optimization
• Sequence to Sequence Learning with Neural Networks
• Teaching Machines to Read and Comprehend
• Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
• Character-Aware Neural Language Models
• On Using Monolingual Corpora in Neural Machine Translation
• Incorporating Copying Mechanism in Sequence-to-Sequence Learning
• Recurrent Convolutional Neural Networks for Discourse Compositionality
• Sentence Compression as Tree Transduction
• Pointing the Unknown Words

Cited by in corpus (68)

• Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond
• Selective Encoding for Abstractive Sentence Summarization
• Incorporating Copying Mechanism in Sequence-to-Sequence Learning
• Pretrained Language Models for Sequential Sentence Classification
• AttSum: Joint Learning of Focusing and Summarization with Neural Attention
• R${}^3$: Reinforced Reader-Ranker for Open-Domain Question Answering
• Classify or Select: Neural Architectures for Extractive Document Summarization
• Efficient Summarization with Read-Again and Copy Mechanism
• Neural Machine Translation with External Phrase Memory
• Graph-based Neural Multi-Document Summarization
• Efficient Adaptation of Pretrained Transformers for Abstractive Summarization
• Abstractive and Extractive Text Summarization using Document Context Vector and Recurrent Neural Networks
• Deep Recurrent Generative Decoder for Abstractive Text Summarization
• IndoLEM and IndoBERT: A Benchmark Dataset and Pre-trained Language Model for Indonesian NLP
• Learning to Extract Coherent Summary via Deep Reinforcement Learning
• 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
• Paraphrase Generation with Deep Reinforcement Learning
• A Multi-task Learning Approach for Improving Product Title Compression with User Search Log Data
• Bidirectional Attentional Encoder-Decoder Model and Bidirectional Beam Search for Abstractive Summarization
• Language Model Pre-training for Hierarchical Document Representations
• Neural Document Summarization by Jointly Learning to Score and Select Sentences
• Liputan6: A Large-scale Indonesian Dataset for Text Summarization
• What comes next? Extractive summarization by next-sentence prediction
• Adapting the Neural Encoder-Decoder Framework from Single to Multi-Document Summarization
• Entity Commonsense Representation for Neural Abstractive Summarization
• Autoencoder as Assistant Supervisor: Improving Text Representation for Chinese Social Media Text Summarization
• Neural Latent Extractive Document Summarization
• Unsupervised Pseudo-Labeling for Extractive Summarization on Electronic Health Records
• Hierarchical Question Answering for Long Documents
• Automatic Generation of Chinese Short Product Titles for Mobile Display
• Reinforced Extractive Summarization with Question-Focused Rewards
• Attention based Sentence Extraction from Scientific Articles using Pseudo-Labeled data
• Improving Semantic Relevance for Sequence-to-Sequence Learning of Chinese Social Media Text Summarization
• AREDSUM: Adaptive Redundancy-Aware Iterative Sentence Ranking for Extractive Document Summarization
• Efficient and Effective Single-Document Summarizations and A Word-Embedding Measurement of Quality
• Joint Learning of Answer Selection and Answer Summary Generation in Community Question Answering
• Automatic generation of reviews of scientific papers
• Contextualized Rewriting for Text Summarization
• Detecting (Un)Important Content for Single-Document News Summarization
• PoinT-5: Pointer Network and T-5 based Financial NarrativeSummarisation
• Unsupervised Summarization by Jointly Extracting Sentences and Keywords
• Exploring Sentence Vector Spaces through Automatic Summarization
• SciSummPip: An Unsupervised Scientific Paper Summarization Pipeline
• Iterative Document Representation Learning Towards Summarization with Polishing
• Earlier Isn't Always Better: Sub-aspect Analysis on Corpus and System Biases in Summarization
• Discriminative Pre-training for Low Resource Title Compression in Conversational Grocery
• Multiple Instance Learning Networks for Fine-Grained Sentiment Analysis
• Multi-Source Pointer Network for Product Title Summarization
• A Hybrid Word-Character Approach to Abstractive Summarization
• Constructing Explainable Opinion Graphs from Review
• Goal-Driven Sequential Data Abstraction
• Facet-Aware Evaluation for Extractive Summarization
• Automatic Text Extractive Summarization Based on Graph and Pre-trained Language Model Attention
• Fact-level Extractive Summarization with Hierarchical Graph Mask on BERT
• Sequence-to-Set Semantic Tagging: End-to-End Multi-label Prediction using Neural Attention for Complex Query Reformulation and Automated Text Categorization
• Learning Sentence Embeddings for Coherence Modelling and Beyond
• A Hierarchical Decoder with Three-level Hierarchical Attention to Generate Abstractive Summaries of Interleaved Texts
• Improving Abstractive Text Summarization with History Aggregation
• Centrality Meets Centroid: A Graph-based Approach for Unsupervised Document Summarization
• Question-Aware Sentence Gating Networks for Question and Answering
• From web crawled text to project descriptions: automatic summarizing of social innovation projects
• Ranking sentences from product description & bullets for better search
• Abstractive Summarization Improved by WordNet-based Extractive Sentences
• Order-Preserving Abstractive Summarization for Spoken Content Based on Connectionist Temporal Classification
• Learning to Summarize Long Texts with Memory Compression and Transfer
• AI-Powered Text Generation for Harmonious Human-Machine Interaction: Current State and Future Directions