Adaptive information retrieval framework and its applications to educational video lectures

Abstract

Information Retrieval (IR) is the discipline that deals with retrieval of unstructured data, especially textual documents, in response to a query or topic, which may itself be unstructured, e.g., a sentence or even another document, or which may be structured, e.g., a Boolean expression. The need for effective methods of automated IR has grown in importance because of the tremendous explosion in the amount of unstructured data, both internal, corporate document collections, and the immensely growing number of document sources on the Internet. The topics covered include: formulation of structured and unstructured queries, topic statements, indexing (including term weighting) of document collections, methods for computing the similarity of queries and documents, classification and routing of documents, in an incoming stream on the basis of topic or need statements, clustering of document collections on the basis of language or topic, and statistical, probabilistic, and semantic methods of analyzing and retrieving documents. There is a growing demand for technology that enable computers to manage and manipulate video and other media sources better. The objective is to build a system to search an archive of NPTEL (National Programme on Technology Enhanced Learning) stock build video clips at lower cost. It also aims to provide on-line access to stored video clips with flexible, effective, and efficient retrieval. Our approach is to construct a rich conceptual indexing system, a simple retrieval algorithm, and an easy to-use browsing interface. The current state of the art in video analysis does not support automated extraction of many interesting conceptual features. The efforts are directed towards elaborating a vocabulary of what those features should be; and on building a practical hand-code indexing system. The existing conceptual indexing approaches of case-based reasoning systems employ representational requirements of intelligent multimedia retrieval systems.