Structured Neural Summarization
Machine Learning
2021-02-04 v4 Computation and Language
Software Engineering
Machine Learning
Abstract
Summarization of long sequences into a concise statement is a core problem in natural language processing, requiring non-trivial understanding of the input. Based on the promising results of graph neural networks on highly structured data, we develop a framework to extend existing sequence encoders with a graph component that can reason about long-distance relationships in weakly structured data such as text. In an extensive evaluation, we show that the resulting hybrid sequence-graph models outperform both pure sequence models as well as pure graph models on a range of summarization tasks.
Cite
@article{arxiv.1811.01824,
title = {Structured Neural Summarization},
author = {Patrick Fernandes and Miltiadis Allamanis and Marc Brockschmidt},
journal= {arXiv preprint arXiv:1811.01824},
year = {2021}
}
Comments
Published in ICLR 2019 https://openreview.net/forum?id=H1ersoRqtm