Guided Neural Language Generation for Abstractive Summarization using Abstract Meaning Representation

08/28/2018
by   Hardy, et al.
0

Recent work on abstractive summarization has made progress with neural encoder-decoder architectures. However, such models are often challenged due to their lack of explicit semantic modeling of the source document and its summary. In this paper, we extend previous work on abstractive summarization using Abstract Meaning Representation (AMR) with a neural language generation stage which we guide using the source document. We demonstrate that this guidance improves summarization results by 7.4 and 10.5 points in ROUGE-2 using gold standard AMR parses and parses obtained from an off-the-shelf parser respectively. We also find that the summarization performance using the latter is 2 ROUGE-2 points higher than that of a well-established neural encoder-decoder approach trained on a larger dataset. Code is available at <https://github.com/sheffieldnlp/AMR2Text-summ>

READ FULL TEXT
research
05/25/2018

Toward Abstractive Summarization Using Semantic Representations

We present a novel abstractive summarization framework that draws on the...
research
08/19/2018

Adapting the Neural Encoder-Decoder Framework from Single to Multi-Document Summarization

Generating an abstract from a set of relevant documents remains challeng...
research
09/04/2019

Mixture Content Selection for Diverse Sequence Generation

Generating diverse sequences is important in many NLP applications such ...
research
02/08/2023

Leveraging Summary Guidance on Medical Report Summarization

This study presents three deidentified large medical text datasets, name...
research
04/23/2017

Deep Keyphrase Generation

Keyphrase provides highly-summative information that can be effectively ...
research
12/07/2020

CX DB8: A queryable extractive summarizer and semantic search engine

Competitive Debate's increasingly technical nature has left competitors ...
research
06/14/2018

Abstract Meaning Representation for Multi-Document Summarization

Generating an abstract from a collection of documents is a desirable cap...

Please sign up or login with your details

Forgot password? Click here to reset