A Sentence Compression Based Framework to Query-Focused Multi-Document Summarization
arXiv:1606.07548
Abstract
We consider the problem of using sentence compression techniques to facilitate query-focused multi-document summarization. We present a sentence-compression-based framework for the task, and design a series of learning-based compression models built on parse trees. An innovative beam search decoder is proposed to efficiently find highly probable compressions. Under this framework, we show how to integrate various indicative metrics such as linguistic motivation and query relevance into the compression process by deriving a novel formulation of a compression scoring function. Our best model achieves statistically significant improvement over the state-of-the-art systems on several metrics (e.g. 8.0% and 5.4% improvements in ROUGE-2 respectively) for the DUC 2006 and 2007 summarization task.
ACL 2013
References in corpus (1)
Cited by in corpus (22)
- Structure-Infused Copy Mechanisms for Abstractive Summarization
- Coarse-grain Fine-grain Coattention Network for Multi-evidence Question Answering
- Actor-Critic based Training Framework for Abstractive Summarization
- Deep Recurrent Generative Decoder for Abstractive Text Summarization
- AQuaMuSe: Automatically Generating Datasets for Query-Based Multi-Document Summarization
- Neural Extractive Text Summarization with Syntactic Compression
- Query-Based Abstractive Summarization Using Neural Networks
- Adapting the Neural Encoder-Decoder Framework from Single to Multi-Document Summarization
- An Entity-Driven Framework for Abstractive Summarization
- Scoring Sentence Singletons and Pairs for Abstractive Summarization
- Fast k-best Sentence Compression
- Analyzing Sentence Fusion in Abstractive Summarization
- Controlling the Amount of Verbatim Copying in Abstractive Summarization
- Closed-Book Training to Improve Summarization Encoder Memory
- Multi-hop Inference for Question-driven Summarization
- Improving the Similarity Measure of Determinantal Point Processes for Extractive Multi-Document Summarization
- Salience Estimation with Multi-Attention Learning for Abstractive Text Summarization
- Discriminative Pre-training for Low Resource Title Compression in Conversational Grocery
- Guiding Extractive Summarization with Question-Answering Rewards
- Balancing Novelty and Salience: Adaptive Learning to Rank Entities for Timeline Summarization of High-impact Events
- Towards Annotating and Creating Sub-Sentence Summary Highlights
- Joint Parsing and Generation for Abstractive Summarization