Strategies for Improving the Efficacy of Fusion Question Answering Systems

Autor:	Julie Smith-David, Gregory Schymik, Jose Antonio Robles-Flores, Robert D. St. Louis
Rok vydání:	2011
Předmět:	World Wide Web Focus (computing) Information Systems and Management Information retrieval Computer science Crowd sourcing Web page Question answering Statistics Probability and Uncertainty Management Information Systems Web site
Zdroj:	International Journal of Business Intelligence Research. 2:46-63
ISSN:	1947-3605 1947-3591
DOI:	10.4018/jbir.2011010104
Popis:	Web search engines typically retrieve a large number of web pages and overload business analysts with irrelevant information. One approach that has been proposed for overcoming some of these problems is automated Question Answering (QA). This paper describes a case study that was designed to determine the efficacy of QA systems for generating answers to original, fusion, list questions (questions that have not previously been asked and answered, questions for which the answer cannot be found on a single web site, and questions for which the answer is a list of items). Results indicate that QA algorithms are not very good at producing complete answer lists and that searchers are not very good at constructing answer lists from snippets. These findings indicate a need for QA research to focus on crowd sourcing answer lists and improving output format.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::27b8522497d3754f857b21886789a380 https://doi.org/10.4018/jbir.2011010104 Zobrazit plný text záznamu