# Multiresolution Graph Attention Networks for Relevance Matching

## TL;DR

This paper introduces a multiresolution graph attention network that effectively captures structural information in long documents for relevance matching with short texts, outperforming existing models.

## Contribution

The paper proposes a novel multiresolution graph attention network that leverages graph convolutional networks and attention mechanisms for short-long text relevance matching.

## Key findings

- Outperforms state-of-the-art deep matching models on two datasets.
- Effectively handles length discrepancy and structural information in long texts.
- Demonstrates significant improvement in relevance matching accuracy.

## Abstract

A large number of deep learning models have been proposed for the text matching problem, which is at the core of various typical natural language processing (NLP) tasks. However, existing deep models are mainly designed for the semantic matching between a pair of short texts, such as paraphrase identification and question answering, and do not perform well on the task of relevance matching between short-long text pairs. This is partially due to the fact that the essential characteristics of short-long text matching have not been well considered in these deep models. More specifically, these methods fail to handle extreme length discrepancy between text pieces and neither can they fully characterize the underlying structural information in long text documents. In this paper, we are especially interested in relevance matching between a piece of short text and a long document, which is critical to problems like query-document matching in information retrieval and web searching. To extract the structural information of documents, an undirected graph is constructed, with each vertex representing a keyword and the weight of an edge indicating the degree of interaction between keywords. Based on the keyword graph, we further propose a Multiresolution Graph Attention Network to learn multi-layered representations of vertices through a Graph Convolutional Network (GCN), and then match the short text snippet with the graphical representation of the document with the attention mechanisms applied over each layer of the GCN. Experimental results on two datasets demonstrate that our graph approach outperforms other state-of-the-art deep matching models.