2008 ContextAwareQuerySuggestion

Subject Headings: IR Query Suggestion Task, Interactive Task, Context-Aware Algorithm, Personalized Algorithm.

Notes

Query suggestion plays an important role in improving the usability of search engines. Although some recently proposed methods can make meaningful query suggestions by mining query patterns from search logs, none of them are context-aware - they do not take into account the immediately preceding queries as context in query suggestion. In this paper, we propose a novel context-aware query suggestion approach which is in two steps. In the offine model-learning step, to address data sparseness, queries are summarized into concepts by clustering a click-through bipartite. Then, from session data a concept sequence suffix tree is constructed as the query suggestion model. In the online query suggestion step, a user's search context is captured by mapping the query sequence submitted by the user to a sequence of concepts. By looking up the context in the concept sequence sufix tree, our approach suggests queries to the user in a context-aware manner. We test our approach on a large-scale search log of a commercial search engine containing 1:8 billion search queries, 2:6 billion clicks, and 840 million query sessions. The experimental results clearly show that our approach outperforms two baseline methods in both coverage and quality of suggestions.

The effectiveness of information retrieval from the web largely depends on whether users can issue queries to search engines, which properly describe their information needs. Writing queries is never easy, because usually queries are short (one or two words on average) [19] and words are ambiguous [5]. To make the problem even more complicated, different search engines may respond differently to the same query. Therefore, there is no “standard” or “optimal” way to issue queries to search engines, and it is well recognized that query formulation is a bottleneck issue in the usability of search engines.
Recently, most commercial search engines such as Google, Yahoo!, Live Search, Ask, and Baidu provide query suggestions to improve usability. That is, by guessing a user's search intent, a search engine suggests queries which may better re°ect the user's information need. A commonly used query suggestion method [1, 3, 19] is to ¯nd similar queries in search logs and use those queries as suggestions for each other. Another approach [8, 10, 11] mines pairs of queries which are adjacent or co-occur in the same query sessions. Although the existing methods may suggest good queries in some cases, none of them are context-aware (they do not take into account the immediately preceding queries as context in query suggestion.)

,