Augmented Abstractive Summarization With Document-LevelSemantic Graph
This addresses a specific bottleneck in abstractive summarization for natural language processing, but it is incremental as it builds on existing graph-based methods.
The paper tackles the problem of abstractive summarization lacking a module to detect vital mentions and relationships within documents by utilizing a semantic graph to boost generation performance, with automatic and human evaluations showing effectiveness.
Previous abstractive methods apply sequence-to-sequence structures to generate summary without a module to assist the system to detect vital mentions and relationships within a document. To address this problem, we utilize semantic graph to boost the generation performance. Firstly, we extract important entities from each document and then establish a graph inspired by the idea of distant supervision \citep{mintz-etal-2009-distant}. Then, we combine a Bi-LSTM with a graph encoder to obtain the representation of each graph node. A novel neural decoder is presented to leverage the information of such entity graphs. Automatic and human evaluations show the effectiveness of our technique.