Efficient Prediction of Difficult Keyword Queries over Databases

Efficient Prediction of Difficult Keyword Queries over Databases

Keyword queries on databases provide easy access to data, but often suffer from low ranking quality, i.e., low precision and/or recall, as shown in recent benchmarks. It would be useful to identify queriesthat are likely to have low ranking quality to improve the user satisfaction. For instance, the system may suggest to the user alternative queries for such hard queries. In this paper, we analyze the characteristics of hard queries and propose a novel framework to measure the degree of difficulty for akeyword query over a database, considering both the structure and the content of the database and thequery results. We evaluate our query difficulty prediction model against two effectiveness benchmarks for popular keyword search ranking methods. Our empirical results show that our model predicts the hard queries with high accuracy. Further, we present a suite of optimizations to minimize the incurred time overhead.

Comments are closed.