Title: Structured Neural Summarization
Authors: Patrick Fernandes, Miltiadis Allamanis, Marc Brockschmidt
Published: 5th November 2018 (Monday) @ 16:12:04
Link: http://arxiv.org/abs/1811.01824v4
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.