Analyzing Sentence Fusion in Abstractive Summarization

10/01/2019
by   Logan Lebanoff, et al.
0

While recent work in abstractive summarization has resulted in higher scores in automatic metrics, there is little understanding on how these systems combine information taken from multiple document sentences. In this paper, we analyze the outputs of five state-of-the-art abstractive summarizers, focusing on summary sentences that are formed by sentence fusion. We ask assessors to judge the grammaticality, faithfulness, and method of fusion for summary sentences. Our analysis reveals that system sentences are mostly grammatical, but often fail to remain faithful to the original article.

READ FULL TEXT
research
05/31/2019

Scoring Sentence Singletons and Pairs for Abstractive Summarization

When writing a summary, humans tend to choose content from one or two se...
research
10/08/2020

Learning to Fuse Sentences with Transformers for Summarization

The ability to fuse sentences is highly attractive for summarization sys...
research
06/09/2011

Inferring Strategies for Sentence Ordering in Multidocument News Summarization

The problem of organizing information for multidocument summarization so...
research
11/23/2019

Joint Parsing and Generation for Abstractive Summarization

Sentences produced by abstractive summarization systems can be ungrammat...
research
10/24/2019

Multi-Document Summarization with Determinantal Point Processes and Contextualized Representations

Emerged as one of the best performing techniques for extractive summariz...
research
07/16/2019

STRASS: A Light and Effective Method for Extractive Summarization Based on Sentence Embeddings

This paper introduces STRASS: Summarization by TRAnsformation Selection ...
research
10/12/2012

Quick Summary

Quick Summary is an innovate implementation of an automatic document sum...

Please sign up or login with your details

Forgot password? Click here to reset