Structure-Infused Copy Mechanisms for Abstractive Summarization

06/14/2018
by   Kaiqiang Song, et al.
0

Seq2seq learning has produced promising results on summarization. However, in many cases, system summaries still struggle to keep the meaning of the original intact. They may miss out important words or relations that play critical roles in the syntactic structure of source sentences. In this paper, we present structure-infused copy mechanisms to facilitate copying important words and relations from a source sentence to a summary sentence. The approach naturally combines the dependency structure of the source sentence with the copy mechanism of an abstractive sentence summarization system. Experimental results demonstrate the effectiveness of incorporating source-side syntactic information in the system, and our proposed approach compares favorably to state-of-the-art methods.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/23/2019

Joint Parsing and Generation for Abstractive Summarization

Sentences produced by abstractive summarization systems can be ungrammat...
research
03/19/2018

Controlling Decoding for More Abstractive Summaries with Copy-Based Networks

Attention-based neural abstractive summarization systems equipped with c...
research
07/06/2018

Sequential Copying Networks

Copying mechanism shows effectiveness in sequence-to-sequence based neur...
research
10/09/2022

HEGEL: Hypergraph Transformer for Long Document Summarization

Extractive summarization for long documents is challenging due to the ex...
research
12/11/2019

Quality of syntactic implication of RL-based sentence summarization

Work on summarization has explored both reinforcement learning (RL) opti...
research
09/26/2021

BioCopy: A Plug-And-Play Span Copy Mechanism in Seq2Seq Models

Copy mechanisms explicitly obtain unchanged tokens from the source (inpu...
research
06/03/2021

To Point or Not to Point: Understanding How Abstractive Summarizers Paraphrase Text

Abstractive neural summarization models have seen great improvements in ...

Please sign up or login with your details

Forgot password? Click here to reset