BERT-QE: Contextualized Query Expansion for Document Re-ranking
Zhi Zheng, Kai Hui, Ben He, Xianpei Han, Le Sun, Andrew Yates
Abstract
Query expansion aims to mitigate the mismatch between the language used in a query and in a document. However, query expansion methods can suffer from introducing non-relevant information when expanding the query. To bridge this gap, inspired by recent advances in applying contextualized models like BERT to the document retrieval task, this paper proposes a novel query expansion model that leverages the strength of the BERT model to select relevant document chunks for expansion. In evaluation on the standard TREC Robust04 and GOV2 test collections, the proposed BERT-QE model significantly outperforms BERT-Large models.
Topics & Concepts
Query expansionComputer scienceRanking (information retrieval)Query optimizationInformation retrievalSargableQuery languageBridge (graph theory)Task (project management)Web search queryWeb query classificationSearch engineInternal medicineEconomicsMedicineManagementTopic ModelingSemantic Web and OntologiesAdvanced Text Analysis Techniques