Learning to Fuse Sentences with Transformers for Summarization

10/08/2020
by   Logan Lebanoff, et al.
0

The ability to fuse sentences is highly attractive for summarization systems because it is an essential step to produce succinct abstracts. However, to date, summarizers can fail on fusing sentences. They tend to produce few summary sentences by fusion or generate incorrect fusions that lead the summary to fail to retain the original meaning. In this paper, we explore the ability of Transformers to fuse sentences and propose novel algorithms to enhance their ability to perform sentence fusion by leveraging the knowledge of points of correspondence between sentences. Through extensive experiments, we investigate the effects of different design choices on Transformer's performance. Our findings highlight the importance of modeling points of correspondence between sentences for effective sentence fusion.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/01/2019

Analyzing Sentence Fusion in Abstractive Summarization

While recent work in abstractive summarization has resulted in higher sc...
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
11/23/2019

Joint Parsing and Generation for Abstractive Summarization

Sentences produced by abstractive summarization systems can be ungrammat...
research
04/07/2023

GEMINI: Controlling the Sentence-level Writing Style for Abstractive Text Summarization

Human experts write summaries using different techniques, including rewr...
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
10/06/2020

Stepwise Extractive Summarization and Planning with Structured Transformers

We propose encoder-centric stepwise models for extractive summarization ...
research
08/25/2020

Extractive Summarizer for Scholarly Articles

We introduce an extractive method that will summarize long scientific pa...

Please sign up or login with your details

Forgot password? Click here to reset