A Graph-based Relevance Matching Model for Ad-hoc Retrieval

Authors

  • Yufeng Zhang Institute of Automation, Chinese Academy of Sciences
  • Jinghao Zhang Institute of Automation, Chinese Academy of Sciences University of Chinese Academy of Sciences
  • Zeyu Cui Institute of Automation, Chinese Academy of Sciences University of Chinese Academy of Sciences
  • Shu Wu Institute of Automation, Chinese Academy of Sciences University of Chinese Academy of Sciences Artificial Intelligence Research, Chinese Academy of Sciences
  • Liang Wang Institute of Automation, Chinese Academy of Sciences University of Chinese Academy of Sciences

DOI:

https://doi.org/10.1609/aaai.v35i5.16599

Keywords:

Web Search & Information Retrieval

Abstract

To retrieve more relevant, appropriate and useful documents given a query, finding clues about that query through the text is crucial. Recent deep learning models regard the task as a term-level matching problem, which seeks exact or similar query patterns in the document. However, we argue that they are inherently based on local interactions and do not generalise to ubiquitous, non-consecutive contextual relationships. In this work, we propose a novel relevance matching model based on graph neural networks to leverage the document-level word relationships for ad-hoc retrieval. In addition to the local interactions, we explicitly incorporate all contexts of a term through the graph-of-word text format. Matching patterns can be revealed accordingly to provide a more accurate relevance score. Our approach significantly outperforms strong baselines on two ad-hoc benchmarks. We also experimentally compare our model with BERT and show our advantages on long documents.

Downloads

Published

2021-05-18

How to Cite

Zhang, Y., Zhang, J., Cui, Z., Wu, S., & Wang, L. (2021). A Graph-based Relevance Matching Model for Ad-hoc Retrieval. Proceedings of the AAAI Conference on Artificial Intelligence, 35(5), 4688-4696. https://doi.org/10.1609/aaai.v35i5.16599

Issue

Section

AAAI Technical Track on Data Mining and Knowledge Management