DeepAI AI Chat
Log In Sign Up

Discrete Optimization for Unsupervised Sentence Summarization with Word-Level Extraction

by   Raphael Schumann, et al.
University of Waterloo
University of Heidelberg

Automatic sentence summarization produces a shorter version of a sentence, while preserving its most important information. A good summary is characterized by language fluency and high information overlap with the source sentence. We model these two aspects in an unsupervised objective function, consisting of language modeling and semantic similarity metrics. We search for a high-scoring summary by discrete optimization. Our proposed method achieves a new state-of-the art for unsupervised sentence summarization according to ROUGE scores. Additionally, we demonstrate that the commonly reported ROUGE F1 metric is sensitive to summary length. Since this is unwillingly exploited in recent work, we emphasize that future evaluation should explicitly group summarization systems by output length brackets.


Learning Non-Autoregressive Models from Search for Unsupervised Sentence Summarization

Text summarization aims to generate a short summary for an input text. I...

BottleSum: Unsupervised and Self-supervised Sentence Summarization using the Information Bottleneck Principle

The principle of the Information Bottleneck (Tishby et al. 1999) is to p...

Experiments in Extractive Summarization: Integer Linear Programming, Term/Sentence Scoring, and Title-driven Models

In this paper, we revisit the challenging problem of unsupervised single...

A Character-Level Length-Control Algorithm for Non-Autoregressive Sentence Summarization

Sentence summarization aims at compressing a long sentence into a short ...

Simple Unsupervised Summarization by Contextual Matching

We propose an unsupervised method for sentence summarization using only ...

Universal Evasion Attacks on Summarization Scoring

The automatic scoring of summaries is important as it guides the develop...

Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting

Inspired by how humans summarize long documents, we propose an accurate ...