Log In Sign Up

A Condense-then-Select Strategy for Text Summarization

by   Hou Pong (Ken) Chan, et al.

Select-then-compress is a popular hybrid, framework for text summarization due to its high efficiency. This framework first selects salient sentences and then independently condenses each of the selected sentences into a concise version. However, compressing sentences separately ignores the context information of the document, and is therefore prone to delete salient information. To address this limitation, we propose a novel condense-then-select framework for text summarization. Our framework first concurrently condenses each document sentence. Original document sentences and their compressed versions then become the candidates for extraction. Finally, an extractor utilizes the context information of the document to select candidates and assembles them into a summary. If salient information is deleted during condensing, the extractor can select an original sentence to retain the information. Thus, our framework helps to avoid the loss of salient information, while preserving the high efficiency of sentence-level compression. Experiment results on the CNN/DailyMail, DUC-2002, and Pubmed datasets demonstrate that our framework outperforms the select-then-compress framework and other strong baselines.


page 1

page 2

page 3

page 4


Neural Document Summarization by Jointly Learning to Score and Select Sentences

Sentence scoring and sentence selection are two main steps in extractive...

Reinforcing Semantic-Symmetry for Document Summarization

Document summarization condenses a long document into a short version wi...

Improving Multi-Document Summarization through Referenced Flexible Extraction with Credit-Awareness

A notable challenge in Multi-Document Summarization (MDS) is the extreme...

A Survey on Neural Abstractive Summarization Methods and Factual Consistency of Summarization

Automatic summarization is the process of shortening a set of textual da...

Abstractive Document Summarization without Parallel Data

Abstractive summarization typically relies on large collections of paire...

Abstractive Summarization Guided by Latent Hierarchical Document Structure

Sequential abstractive neural summarizers often do not use the underlyin...

MemSum: Extractive Summarization of Long Documents using Multi-step Episodic Markov Decision Processes

We introduce MemSum (Multi-step Episodic Markov decision process extract...