Multiresolution Graph Attention Networks for Relevance Matching

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.

Accepted by CIKM 2018

References in corpus (11)

• Semi-Supervised Classification with Graph Convolutional Networks
• Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
• Convolutional Neural Network Architectures for Matching Natural Language Sentences
• A Deep Relevance Matching Model for Ad-hoc Retrieval
• IRGAN: A Minimax Game for Unifying Generative and Discriminative Information Retrieval Models
• A Deep Architecture for Semantic Matching with Multiple Positional Sentence Representations
• An Information Retrieval Approach to Short Text Conversation
• Text Matching as Image Recognition
• Bilateral Multi-Perspective Matching for Natural Language Sentences
• Reinforced Mnemonic Reader for Machine Reading Comprehension
• MatchZoo: A Toolkit for Deep Text Matching

Cited by in corpus (6)

• Dual Graph Attention Networks for Deep Latent Representation of Multifaceted Social Effects in Recommender Systems
• Learning to Generate Questions by Learning What not to Generate
• GC-LSTM: Graph Convolution Embedded LSTM for Dynamic Link Prediction
• Graph-based Hierarchical Relevance Matching Signals for Ad-hoc Retrieval
• Coherent Comment Generation for Chinese Articles with a Graph-to-Sequence Model
• Matching Article Pairs with Graphical Decomposition and Convolutions