It is crucial for query auto-completion to accurately predict what a user is typing. Given a query prefix and its context (e.g., previous queries), conventional context-aware approaches often produce relevant queries to the context. The purpose of this paper is to investigate the feasibility of exploiting the context to learn user reformulation behavior for boosting prediction performance. We first conduct an in-depth analysis of how the users reformulate their queries. Based on the analysis, we propose a supervised approach to query auto-completion, where three kinds of reformulation-related features are considered, including term-level, query-level and session-level features. These features carefully capture how the users change preceding queries along the query sessions. Extensive experiments have been conducted on the large-scale query log of a commercial search engine. The experimental results demonstrate a significant improvement over 4 competitive baselines.
Due to the ever-growing popularity mobile devices of various kinds have received worldwide, the demands on large-scale wireless network infrastructure development and enhancement have been rapidly swelling in recent years. A mobile device holder can get online at a wireless network access point, which covers a limited area. When the client leaves the access point, there will be a temporary disconnection until he/she enters the coverage of another access point. Even when the coverages of two neighboring access points overlap, there is still work to do to make the wireless connection smoothly continue. The action of one wireless network access point passing a client to another access point is referred to as the handover. During handover, for security concerns, the client and the new access point should perform mutual authentication before any Internet access service is practically gained/provided. If the handover protocol is inefficient, in some cases discontinued Internet service will happen. In 2013, Li et al. proposed a fast handover authentication mechanism for wireless mesh network (WMN) based on tickets. Unfortunately, Li et al.’s work came with some weaknesses. For one thing, some sensitive information such as the time and date of expiration is sent in plaintext, which increases security risks. For another, Li et al.’s protocol includes the use of high-quality tamper-proof devices (TPDs), and this unreasonably high equipment requirement limits its applicability. In this paper, we shall propose a new efficient handover authentication mechanism. The new mechanism offers a higher level of security on a more scalable ground with the client’s privacy better preserved. The results of our performance analysis suggest that our new mechanism is superior to some similar mechanisms in terms of authentication delay.
In this paper, we propose a new idea called ranking consistency in web search. Relevance ranking is one of the biggest problems in creating an effective web search system. Given some queries with similar search intents, conventional approaches typically only optimize ranking models by each query separately. Hence, there are inconsistent rankings in modern search engines. It is expected that the search results of different queries with similar search intents should preserve ranking consistency. The aim of this paper is to learn consistent rankings in search results for improving the relevance ranking in web search. We then propose a re-ranking model aiming to simultaneously improve relevance ranking and ranking consistency by leveraging knowledge bases and search logs. To the best of our knowledge, our work offers the first solution to improving relevance rankings with ranking consistency. Extensive experiments have been conducted using the Freebase knowledge base and the large-scale query-log of a commercial search engine. The experimental results show that our approach significantly improves relevance ranking and ranking consistency. Two user surveys on Amazon Mechanical Turk also show that users are sensitive and prefer the consistent ranking results generated by our model.