Content-Based Mining of Query Replacements

This dissertation introduces the problem of content-based query replacement. It motivatesthe term correlation modeled using MRFs and thesampling based technique to learn thesearch phrase definitions. These definitions areused as alternative queries to achieve higheraccuracy in several retrieval tasks.Retrieving relevant documents while eliminatingirrelevant documents for an user'squery is a challenging task which involves a goodunderstanding of the relation betweenthe data and the query as well as developingalgorithms that can efficiently measure therelevance of the data to the query. As part of thisdissertation, we have developed a hypothesis toreduce the problem of mining search phrasedefinitions significantlyby modeling the joint distribution of terms as aproduct of conditional distributions,modeled as a Markov Random Field. We assume thatthere exists an underlying jointdistribution among terms that are used to describethe search phrase. The modelingwe propose is a condensed representation of inter-term relationship and it appears tocapture insight statistics among terms.describes a target phrase.

Autorentext

Hung Viet Nguyen was born in Hanoi, Vietnam. He obtained a Bachelor in Science from Vietnam National University, Hanoi. He then obtained a Master from University of Cambridge, UK. Next, he went to the Valley of the Sun and got a Ph.D from Arizona State University, USA. All of his degrees were in Computer Science.