Learning to Rank Query Recommendations by Semantic Similarities
This work addresses the need for better query recommendations in search engines to help users access information more rapidly, though it is incremental as it builds on existing ranking strategies.
The paper tackles the problem of identifying helpful query reformulations from search engine logs, proposing a method that combines click-based, topic-based, and session-based ranking strategies with supervised learning to maximize semantic similarity and diversity in recommendations. The result shows that this combination significantly outperforms any individual strategy when evaluated on logs from a Japanese web search engine.
Logs of the interactions with a search engine show that users often reformulate their queries. Examining these reformulations shows that recommendations that precise the focus of a query are helpful, like those based on expansions of the original queries. But it also shows that queries that express some topical shift with respect to the original query can help user access more rapidly the information they need. We propose a method to identify from the query logs of past users queries that either focus or shift the initial query topic. This method combines various click-based, topic-based and session based ranking strategies and uses supervised learning in order to maximize the semantic similarities between the query and the recommendations, while at the same diversifying them. We evaluate our method using the query/click logs of a Japanese web search engine and we show that the combination of the three methods proposed is significantly better than any of them taken individually.