AttSum: Joint Learning of Focusing and Summarization with Neural Attention

Abstract

Query relevance ranking and sentence saliency ranking are the two main tasks in extractive query-focused summarization. Previous supervised summarization systems often perform the two tasks in isolation. However, since reference summaries are the trade-off between relevance and saliency, using them as supervision, neither of the two rankers could be trained well. This paper proposes a novel summarization system called AttSum, which tackles the two tasks jointly. It automatically learns distributed representations for sentences as well as the document cluster. Meanwhile, it applies the attention mechanism to simulate the attentive reading of human behavior when a query is given. Extensive experiments are conducted on DUC query-focused summarization benchmark datasets. Without using any hand-crafted features, AttSum achieves competitive performance. It is also observed that the sentences recognized to focus on the query indeed meet the query need.

10 pages, 1 figure

References in corpus (4)

• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• Natural Language Processing (almost) from Scratch
• End-to-end Continuous Speech Recognition using Attention-based Recurrent NN: First Results
• Neural Summarization by Extracting Sentences and Words

Cited by in corpus (19)

• A Hierarchical Structured Self-Attentive Model for Extractive Document Summarization (HSSAS)
• Classify or Select: Neural Architectures for Extractive Document Summarization
• Graph-based Neural Multi-Document Summarization
• Deep Recurrent Generative Decoder for Abstractive Text Summarization
• Discourse-Aware Neural Extractive Text Summarization
• A Semantic Relevance Based Neural Network for Text Summarization and Text Simplification
• A Multi-task Learning Approach for Improving Product Title Compression with User Search Log Data
• QBSUM: a Large-Scale Query-Based Document Summarization Dataset from Real-world Applications
• Unsupervised Pseudo-Labeling for Extractive Summarization on Electronic Health Records
• Multi-hop Inference for Question-driven Summarization
• Query-Focused EHR Summarization to Aid Imaging Diagnosis
• Product Title Refinement via Multi-Modal Generative Adversarial Learning
• Improving Online Forums Summarization via Hierarchical Unified Deep Neural Network
• Latent Semantic Analysis Approach for Document Summarization Based on Word Embeddings
• Joint Lifelong Topic Model and Manifold Ranking for Document Summarization
• Question-Aware Sentence Gating Networks for Question and Answering
• Abstractive Summarization Improved by WordNet-based Extractive Sentences
• AI-Powered Text Generation for Harmonious Human-Machine Interaction: Current State and Future Directions
• Generating an Overview Report over Many Documents