No abstract

A search engine infrastructure must be able to provide the same quality of service to all queries received during a day. During normal operating conditions, the demand for resources is considerably lower than under peak conditions, yet an oversized infrastructure would result in an unnecessary waste of computing power. A possible solution adopted in this situation might consist of defining a maximum threshold processing time for each query, and dropping queries for which this threshold elapses, leading to disappointed users. In this paper, we propose and evaluate a different approach, where, given a set of different query processing strategies with differing efficiency, each query is considered by a framework that sets a maximum query processing time and selects which processing strategy is the best for that query, such that the processing time for all queries is kept below the threshold. The processing time estimates used by the scheduler are learned from past queries. We experimentally validate our approach on 10,000 queries from a standard TREC dataset with over 50 million documents, and we compare it with several baselines. These experiments encompass testing the system under different query loads and different maximum tolerated query response times. Our results show that, at the cost of a marginal loss in terms of response quality, our search system is able to answer 90% of queries within half a second during times of high query volume.

Abstract. While Web search engines are built to cope with a large number of queries, query traffic can exceed the maximum query rate supported by the underlying computing infrastructure. We study how response times and results vary when, in presence of high loads, some queries are either interrupted after a fixed time threshold elapses or dropped completely. Moreover, we introduce a novel dropping strategy, based on machine learned performance predictors to select the queries to drop in order to sustain the largest possible query rate with a relative degradation in effectiveness.

Abstract. Query recommender systems give users hints on possible interesting queries relative to their information needs. Most query recommenders are based on static knowledge models built on the basis of past user behaviors recorded in query logs. These models should be periodically updated, or rebuilt from scratch, to keep up with the possible variations in the interests of users. We study query recommender algorithms that generate suggestions on the basis of models that are updated continuously, each time a new query is submitted. We extend two stateof-the-art query recommendation algorithms and evaluate the effects of continuous model updates on their effectiveness and efficiency. Tests conducted on an actual query log show that contrasting model aging by continuously updating the recommendation model is a viable and effective solution.