CAREER: User-centered Adaptive Information Retrieval

信息检索是指从大量的文本中发现信息，是克服信息过载的最有用的技术之一。例如，网络搜索引擎现在是每个人在网络上查找信息的必要工具。现有的信息检索系统本质上是非最佳的，因为检索决策主要是基于当前查询和文档集合做出的，而没有考虑有关用户和搜索上下文的信息。该项目旨在消除现有检索方法的这一局限性，并正式开发一种新的检索范式--以用户为中心的自适应信息检索(UCAIR)，在该范式中，用户信息和搜索上下文都被利用来提高检索性能。该项目的研究包括：(1)开发一个基于贝叶斯决策理论的新的UCAIR框架；(2)开发新的语言模型来开发用户信息和搜索上下文，以提高检索精度；(3)开发新的检索方法，以优化整个检索会话的长期检索效用；(4)开发新的检索方法，以利用用户的相似性，根据其他类似用户的信息更好地推断特定用户的信息需求；以及(5)开发用于搜索Web和生物信息学文献的UCAIR原型系统。该项目将通过为UCAIR开发一个统一的正式框架，开发各种利用用户信息和搜索上下文的检索方法来提高检索精度，从而推动信息检索的发展，这将直接导致所有领域的更有效的信息检索应用。研究成果还将加强现有的信息检索课程，改善信息技术从业人员的教育。项目网站http://sifaka.cs.uiuc.edu/ucair/将用于传播研究成果。

Information Retrieval (IR) refers to finding information from large amounts of text, and is among the most useful technologies for overcoming information overload. For example, Web search engines are now essential tools for everyone to find information on the Web. Existing IR systems are inherently non-optimal because the retrieval decision is made primarily based on the current query and the document collection without considering information about the user and search context. This project seeks to eliminate this limitation of the existing retrieval methods and formally develop a new retrieval paradigm called user-centered adaptive information retrieval (UCAIR), in which user information and search context are both exploited to improve retrieval performance. This project includes research on: (1) developing a new UCAIR framework based on Bayesian decision theory; (2) developing new language models to exploit user information and search context to improve retrieval accuracy; (3) developing new retrieval methods to optimize the long-term retrieval utility over an entire retrieval session; (4) developing new retrieval methods to leverage user similarities to better infer one particular user's information need based on information about other similar users; and (5) developing prototype UCAIR systems for searching the Web and bioinformatics literature. The project will advance the state of the art of IR through developing a unified formal framework for UCAIR, a variety of retrieval methods for exploiting user information and search context to improve retrieval accuracy, which will directly lead to more effective information retrieval applications in all domains. The research results will also enhance the current IR curricula, improving education of information technology workforce. The project Web site http://sifaka.cs.uiuc.edu/ucair/ will be used for research results dissemination.