Question Answering and Generation

Question Answering and Generation

Arthur C. Graesser (The University of Memphis, USA), Vasile Rus (The University of Memphis, USA), Zhiqiang Cai (The University of Memphis, USA) and Xiangen Hu (The University of Memphis, USA)
DOI: 10.4018/978-1-60960-741-8.ch001


Automated Question Answering and Asking are two active areas of Natural Language Processing with the former dominating the past decade and the latter most likely to dominate the next one. Due to the vast amounts of information available electronically in the Internet era, automated Question Answering is needed to fulfill information needs in an efficient and effective manner. Automated Question Answering is the task of providing answers automatically to questions asked in natural language. Typically, the answers are retrieved from large collections of documents. While answering any question is difficult, successful automated solutions to answer some type of questions, so-called factoid questions, have been developed recently, culminating with the just announced Watson Question Answering system developed by I.B.M. to compete in Jeopardy-like games. The flip process, automated Question Asking or Generation, is about generating questions from some form of input such as a text, meaning representation, or database. Question Asking/Generation is an important component in the full gamut of learning technologies, from conventional computer-based training to tutoring systems. Advances in Question Asking/Generation are projected to revolutionize learning and dialogue systems. This chapter presents an overview of recent developments in Question Answering and Generation starting with the landscape of questions that people ask.
Chapter Preview

Question Quality, Complexity, And Taxonomies

An important initial step in a Question Answering or Generation project is to take stock of the landscape of question categories so that researchers can specify what types of questions they have in mind, as well as the educational context (Rus, Cai, & Graesser, 2007). This section identifies some QG categories, taxonomies, and dimensions that might be considered. The complexity and quality of the questions systematically vary across the broad landscape of questions. Finding the relevant criteria of question quality is a key requirement for good performance of QG systems. What we present in this section is merely the tip of the iceberg.

Question taxonomies have been proposed by researchers who have developed models of Question Answering and Generation in the fields of artificial intelligence, computational linguistics (Voorhees, 2001), discourse processing, education and a number of other fields in the cognitive sciences (for a review, see Graesser, Ozuru, & Sullins, 2009).

Complete Chapter List

Search this Book: