Modules and Information Retrieval Facilities of the Human Use Regulatory Affairs Advisor (HURAA)

Autor/inn/en	Graesser, Arthur C.; Person, Natalie K.; Jackson, G. Tanner; Toth, Jozsef A.
Titel	Modules and Information Retrieval Facilities of the Human Use Regulatory Affairs Advisor (HURAA)
Quelle	In: International Journal on E-Learning, 3 (2004) 4, S.29-39 (11 Seiten)Infoseite zur Zeitschrift PDF als Volltext Verfügbarkeit
Sprache	englisch
Dokumenttyp	gedruckt; online; Zeitschriftenaufsatz
ISSN	1537-2456
Schlagwörter	Information Retrieval; Internet; Glossaries; Word Frequency; Natural Language Processing; Ethics; Research Methodology; Human Body; Information Seeking; Federal Regulation + Suchen Sie Ihr Suchwort? Glossary; Glossar; Word analysis; Frequency; Wortanalyse; Häufigkeit; Natürliche Sprache; Ethik; Research method; Forschungsmethode; Menschlicher Körper; Informationserschließung; Bundeskompetenz
Abstract	The Human Use Regulatory Affairs Advisor (HURAA) is an Internet facility that provides help and training on the ethical use of human subjects in research, based on documents and regulations in United States Federal agencies. HURAA has a number of standard features of conventional web facilities and computer-based training, such as hypertext, multimedia, help modules, glossaries, archives, links to other sites, and page-turning didactic instruction. HURAA also has more intelligent features: (1) an animated conversational agent that serves as a navigational guide for the Internet facility, (2) lessons with case-based and explanation-based reasoning, (3) document retrieval though natural language queries, and (4) a context-sensitive Frequently Asked Questions, called Point & Query. The primary focus of this article is on facilities that retrieve documents through natural language queries. This paper first describes the major modules and features of HURAA, and subsequently evaluates the performance of document retrieval through natural language questions. Experts rated the quality of retrieved paragraphs from documents on relevance and informativity with respect to answering the questions. Comparisons were made between different retrieval algorithms (including latent semantic analysis, glossary word overlap, and a word frequency weighted metric) and between the different amounts of context surrounding the question. (Author).
Anmerkungen	Association for the Advancement of Computing in Education, P.O. Box 1545, Chesapeake, VA 23327-1545. Tel: 757-366-5606.
Erfasst von	ERIC (Education Resources Information Center), Washington, DC
Update	2017/4/10