Modeling multiple interactions with a Markov random field in query expansion for session search |
| |
Authors: | Jingfei Li Xiaozhao Zhao Peng Zhang Dawei Song |
| |
Affiliation: | 1. Tianjin Key Laboratory of Cognitive Computing and Application, School of Computer Science and Technology, Tianjin University, Tianjin, China;2. National Computer Network Emergency Response Technical Team/Coordination Center of China, Beijing, China;3. Department of Computing and Communications, The Open University, Milton Keynes, UK |
| |
Abstract: | How to automatically understand and answer users' questions (eg, queries issued to a search engine) expressed with natural language has become an important yet difficult problem across the research fields of information retrieval and artificial intelligence. In a typical interactive Web search scenario, namely, session search, to obtain relevant information, the user usually interacts with the search engine for several rounds in the forms of, eg, query reformulations, clicks, and skips. These interactions are usually mixed and intertwined with each other in a complex way. For the ideal goal, an intelligent search engine can be seen as an artificial intelligence agent that is able to infer what information the user needs from these interactions. However, there still exists a big gap between the current state of the art and this goal. In this paper, in order to bridge the gap, we propose a Markov random field–based approach to capture dependence relations among interactions, queries, and clicked documents for automatic query expansion (as a way of inferring the information needs of the user). An extensive empirical evaluation is conducted on large‐scale web search data sets, and the results demonstrate the effectiveness of our proposed models. |
| |
Keywords: | Markov random field multiple interactions query expansion session search |
|
|