Collaborative Research: Supporting Effective Access Through User-and Topic-Based Language Models

这个合作项目结合了马萨诸塞大学的Bruce Croft教授和James Allan教授在开发和测试信息检索模型和系统方面的专业知识和经验，以及罗格斯大学的Nicholas Belkin教授在交互系统中的用户建模和用户研究方面的专业知识和经验。支持信息检索和过滤的工具已经变得很常见，但在许多重要方面，它们的表现平平。他们犯的错误对用户来说是显而易见的和令人恼火的，相关的文档通常会与许多完全无关的其他文档混在一起。这些问题大大降低了使用这些工具的人的生产力和效率，无论是在教育、科学、商业还是政府部门。该项目研究了一种新的用户和主题建模方法，该方法有可能显著提高信息访问和过滤的有效性。这种方法是基于最近对信息检索的语言模型的研究。语言模型似乎捕获了在早期实验中观察到的用户和领域建模的重要方面，基于文档语言模型的检索技术已被证明是非常有效的。该项目结合了使用TREC数据的标准研究方法、实验室环境中的实验和观察性用户研究，以及对具有多个用户的操作环境中的影响的研究。它将极大地促进对用户模型和主题模型对信息索引、检索和访问等重要问题的影响的理解。

This collaborative project combines the expertise and experience of Professors Bruce Croft and James Allan at the University of Massachusetts in the development and testing of information retrieval models and systems, with that of Professor Nicholas Belkin at Rutgers University in user modeling and user studies in interactive systems. Tools to support information retrieval and filtering have become common, but in many important respects their performance is mediocre. They make mistakes that are obvious and aggravating to users, and relevant documents are usually mixed with many others that are totally unrelated. These problems significantly lower the productivity and effectiveness of people using the tools, whether in education, science, business, or government. This project investigates a new approach to user and topic modeling that has the potential to significantly improve the effectiveness of information access and filtering. This approach is based on recent research on language models for information retrieval. Language models appear to capture the important aspects of user and domain modeling that have been observed in earlier experiments, and retrieval techniques based on document language models have been shown to be very effective. This project combines standard research methodology using TREC data, experimental and observational user studies in laboratory settings, and studies of the impact in operational environments with many users. It will significantly advance understanding of the impact of user- and topic-models on the important problems of information indexing, retrieval, and access.