Matching Article Pairs with Graphical Decomposition and Convolutions

TL;DR

This paper introduces a novel graph-based approach for matching long articles by representing them as concept interaction graphs and employing graph convolutions, significantly improving performance over existing methods.

Contribution

The paper proposes the Concept Interaction Graph model and a new matching framework for long articles, along with two large datasets for evaluation.

Findings

Significant performance improvements over state-of-the-art methods

Effective modeling of complex interactions in long articles

Creation of two large datasets for article matching evaluation

Abstract

Identifying the relationship between two articles, e.g., whether two articles published from different sources describe the same breaking news, is critical to many document understanding tasks. Existing approaches for modeling and matching sentence pairs do not perform well in matching longer documents, which embody more complex interactions between the enclosed entities than a sentence does. To model article pairs, we propose the Concept Interaction Graph to represent an article as a graph of concepts. We then match a pair of articles by comparing the sentences that enclose the same concept vertex through a series of encoding techniques, and aggregate the matching signals through a graph convolutional network. To facilitate the evaluation of long article matching, we have created two datasets, each consisting of about 30K pairs of breaking news articles covering diverse topics in the open domain. Extensive evaluations of the proposed methods on the two datasets demonstrate significant improvements over a wide range of state-of-the-art methods for natural language matching.