Poster
Structured Neural Summarization
Patrick Fernandes · Miltiadis Allamanis · Marc Brockschmidt
Great Hall BC #63
Keywords: [ source code ] [ graphs ] [ summarization ]
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.
Live content is unavailable. Log in and register to view live content