MICO: Selective Search with Mutual Information Co-training
This work addresses efficiency challenges in search systems for users and developers, but it appears incremental as it builds on existing selective search methods with a novel co-training approach.
The paper tackles the problem of reducing latency and computation in large-scale search systems by proposing MICO, a mutual information co-training framework for selective search that clusters documents and routes queries to relevant clusters using minimal supervision from search logs. The result is a significant improvement in performance on multiple metrics, outperforming existing competitive baselines.
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.