Back to Search Start Over

MICO: Selective Search with Mutual Information Co-training

Authors :
Wang, Zhanyu
Zhang, Xiao
Yun, Hyokun
Teo, Choon Hui
Chilimbi, Trishul
Source :
Proceedings of the 29th International Conference on Computational Linguistics (COLING). 2022
Publication Year :
2022

Abstract

In contrast to traditional exhaustive search, selective search first clusters documents into several groups before all the documents are searched exhaustively by a query, to limit the search executed within one group or only a few groups. Selective search is designed to reduce the latency and computation in modern large-scale search systems. In this study, we propose MICO, a Mutual Information CO-training framework for selective search with minimal supervision using the search logs. After training, MICO does not only cluster the documents, but also routes unseen queries to the relevant clusters for efficient retrieval. In our empirical experiments, MICO significantly improves the performance on multiple metrics of selective search and outperforms a number of existing competitive baselines.

Details

Database :
arXiv
Journal :
Proceedings of the 29th International Conference on Computational Linguistics (COLING). 2022
Publication Type :
Report
Accession number :
edsarx.2209.04378
Document Type :
Working Paper