Matching Article Pairs with Graphical Decomposition and Convolutions
Bang Liu, Di Niu, Haojie Wei, Jinghong Lin, Yancheng He, Kunfeng Lai, Yu Xu
TL;DR
Long-document pair matching is challenging due to complex interactions in longer texts. The authors introduce Concept Interaction Graphs (CIGs) to decompose articles into concept-centered subgraphs and match article pairs via per-concept encodings and graph convolutions. They release CNSE and CNSS datasets and demonstrate substantial gains over term-based and neural baselines, confirming the benefits of graphical decomposition and GCN-based aggregation. The approach offers a scalable, end-to-end framework suitable for news clustering and related document understanding tasks.
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.