Expectation Propagation in GenSpace Graphs for Summarization

Expectation Propagation in ExGen Graphs for Summarization: Preliminary Report

Summarization based on expected distribution domain generalization (ExGen) graphs aggregates data into summaries in many ways and identifies summaries that are far from user expectations, i.e., interesting. In this paper, we tackle two problems. First, we propose how to consistently propagate an expected distribution given by the user for one node to the entire ExGen graph. Secondly, we propose...

Finding Interesting Summaries in Genspace Graphs

Graph Hybrid Summarization

One solution to process and analysis of massive graphs is summarization. Generating a high quality summary is the main challenge of graph summarization. In the aims of generating a summary with a better quality for a given attributed graph, both structural and attribute similarities must be considered. There are two measures named density and entropy to evaluate the quality of structural and at...

Graph-based Neural Multi-Document Summarization

We propose a neural multi-document summarization (MDS) system that incorporates sentence relation graphs. We employ a Graph Convolutional Network (GCN) on the relation graphs, with sentence embeddings obtained from Recurrent Neural Networks as input node features. Through multiple layer-wise propagation, the GCN generates high-level hidden sentence features for salience estimation. We then use ...

Gates

Gates are a new notation for representing mixture models and context-sensitive independence in factor graphs. Factor graphs provide a natural representation for message-passing algorithms, such as expectation propagation. However, message passing in mixture models is not well captured by factor graphs unless the entire mixture is represented by one factor, because the message equations have a c...