A Survey and Evaluation of State-of-the-Art Intelligent Question Routing Systems

Abstract

In spite of great developments in artificial intelligence, human brain is still more powerful, concerning the comprehension and manipulation with partially known facts. One domain where this is prominent is related to a problem of question answering. When it comes to giving the answers, especially those that do not explicitly exist in the text corpus, the advantages of a human expert are abilities such as explaining, combining complex answers, and abstract reasoning. This paper represents a survey of the existing research in the domain of intelligent question routing. The survey starts from an original presentation paradigm that generalizes the essence of approaches found in the open literature. The presentation paradigm includes three basic processing stages related to the three major problems of system implementation: question analysis, question forwarding, and users’ knowledge profiling. Various research efforts use different approaches for implementation of each one of the basic processing stages. Each particular approach is described here using the same template. All these approaches are enlisted, discussed, and presented within a table, for easier comparison. The outcome of this analysis is a proposal for a new approach that tackles identified problems.

Real-Time Community Question Answering

“…Previous research on question recommendation focused more on matching questions and potential answerers based on user interest, expertise and availability [16], while less effort was made on question recommendation considering question types, e.g., questions with local intent. Our preliminary study results indicate that location proximity is an important factor for finding potential answerers to answer such questions besides relevance.…”

“…Realtime QA systems often use this strategy [18,36]. A detailed survey of the question recommendation methods can be found in [16].…”

A Theoretical Conversation about Responses to Information Overload

“…The "model [takes] into account the common denominators for all information, which are Syntax, Semantics, and Pragmatics, as defined by semiotician and philosopher Morris" [6]. These definitions reach out to discussions of artificial intelligence modelling with Furlan, et al [19], studies in decision science, linguistics, and more; however the syntax and semantics of information are highly relevant to discussions of the quality element to overload. Pragmatics also allows individuals to parse available information, connecting filtering and management solutions for overload issues.…”

“…Bawden & Robinson (2009) review models of information behavior and suggestions from information managers, concluding with a need for further study including information history and diverse behaviors of information seeking. While much discussion aims to empower the individual, "[w]hen it comes to giving the answers, especially those that do not explicitly exist in the text corpus, the advantages of a human expert are abilities such as explaining, combining complex answers, and abstract reasoning" [19]. These findings from Furlan et al succinctly demonstrate that we cannot cut information purveyors out of the equation.…”