Content area
Full Text
Best young professionals 2
Edited by Elke Greifeneder
Introduction
Conversational agents: origins and types
As modern libraries continue to evolve in the information age, the problem of how to best access information and take advantage of technological advances without introducing new barriers remains a compelling puzzle. The impact of internet, and computer technologies on the library paradigm is unmistakable: even small rural Canadian libraries may offer web sites and an online public access catalogue (OPAC). Where to next? We make the case that Natural Language Interaction (NLI) systems, human-computer interfaces designed to simulate conversation with a real person, are an effective, appropriate complement to many existing library services and may be the key to unlocking solutions to future interactions with information.
NLI is a part of the broader fields of Natural Language Processing (NLP) and Artificial Intelligence (AI). Most internet users have, perhaps unknowingly, already had some contact with NLP technologies in the form of search engines and machine translation tools and with AI - through video games and financial tools. NLP studies the structure, function, and use of language, and organizes it into computational models to design and develop language-related software applications ([25] Joshi, 1999). The field of AI focuses on intelligent computer systems, those that exhibit the characteristics we typically associate with intelligence in human behavior such as understanding language, learning, and problem solving ([4] Barr and Feigenbaum, 1982). As a synthesis of these two fields, the promise of NLI is the ability to provide believable, personalized, and human-like interaction with computers in natural languages like English or French.
For our purposes, we identify two realms within NLI: "chatbots" (also known as text-based conversational agents, artificial conversation entities, chatterboxes, or simply bots), where interaction is limited purely to text input and output; and "embodied conversational agents" (ECA) 1, where the computer interface "is represented as a human body, that uses its face and body in a human-like way in conversation with the user" ([17] Foster, 2007, p. 828) and incorporates animations that are synchronized with the system's linguistic behaviors. Historically, text-based chatbots simply aimed at free-flowing conversations with the user, while ECAs generally serve a particular purpose, such as providing information to users or aiding them with a task. Due to animation, ECAs...