Probabilistic Retrieval of Full-Text Document Collections Using Logistic Regression

该项目开发和测试了文本检索的新概率方法。使用逻辑回归的统计技术，文档按照与查询相关的估计概率排序。这些方法在由NIST（美国国家标准与技术研究院）和DARPA（美国国防高级研究计划局）赞助的TREC（文本检索会议）系列会议的文档集合和查询中进行了严格的性能实验。具体而言，本项目对逻辑回归检索进行了以下几个方面的研究：(1)不同逻辑回归检索模型的比较；(2)智能布尔滤波与逻辑回归相结合的新理论模型；(3)模型在中文和西班牙语检索中的应用。该项目将通过开发完善的检索过程理论模型来推进现代文本和文档检索的进展，这些模型在数百万个文档的实验测试中实现了高性能。本研究将有助于理解多语言检索的机制，并将其方法应用于中文和西班牙文的查询和文献收集。

This project develops and tests new probabilistic approaches to text retrieval. Using the statistical technique of logistic regression, documents are ranked in order of estimated probability of relevance with respect to a query. The methods are subjected to rigorous performance experiments with the collections of documents and queries of the TREC (Text REtrieval Conference) series of conferences sponsored by NIST (National Institute of Standards and Technology) and DARPA (Defense Advanced Research Projects Agency). Specifically the project investigates logistic regression retrieval in the following areas: (1) comparison of different logistic regression retrieval models; (2) new theoretical models which combine intelligent Boolean filtering with logistic regression; and (3) application of the models to Chinese and Spanish language retrieval. This project will advance the progress in modern text and document retrieval by developing sound theoretical models of the retrieval process, models which achieve high performance in experimental tests on millions of documents. The research will contribute to understanding of themechanisms of multilingual retrieval by applying its methodologies to queries and document collections in Chinese and Spanish.