II-NEW: Acquiring infrastructure for Artificial Intelligence, Natural Language Processing and Information Retrieval

点击翻译按钮获取中文摘要

This proposal seeks to obtain funding to acquire computinginfrastructure to perform cross-disciplinary research in artificialintelligence, natural language processing, bioinformatics, socialnetworks and related fields. In particular, the projects that willbe supported by the infrastructure acquired include developing algorithmsand architectures for large-scale ontology alignment, particularly inthe biomedical domain; mining Wikipedia and similar Web-based sourcesfor geographical, temporal and ontological information; performingnamed entity recognition in biomedical and other domains; performingcomputational motivational and content analysis of socially generatedcontent such a blogs and micro-blogs; undertaking corpus-based computationallinguistics research in under-studied and possibly endangered languages fromIndia and other locations; developing better-performing algorithms for geneexpression analysis; and developing, implementing and comparing algorithmsfor protein structure prediction, particularly proteins that containcoiled-coil structures. These projects deal with large amounts of dataand information and processing such data and information requires largeamounts of computing power. Our proposal seeks to acquire adequate andflexible computing hardware to facilitate problem-solving in these and otherareas, so that current and future problems can be solved felicitously. The infrastructure acquired will enable cutting-edge research by Ph.D.,Masters and undergraduate students, including REU site students, in avariety of cross-disciplinary topics that employ ideas and innovationsin artificial intelligence, machine learning and information retrieval.For example, the results of our research may enable creations of systemsthat discover overlaps and matches among large medical ontologies so thatpainstakingly created domain-specific information can be fused, comparedand utilized better; and may assist in creating programs that assist inautomatically understanding and/or visualizing content of socially-generatedWebsites such as Wikipedia and Twitter.For further information see the project web site at the URL:http://www.cs.uccs.edu/~kalita.