A chatbot system as a tool to animate a corpus

1 Introduction " Before there were computers, we could distinguish persons from non-persons on the basis of an ability to participate in conversations. But now, we have hybrids operating between person and non persons with whom we can talk in ordinary language. " (Colby 1999). Human machine conversation as a technology integrates different areas where the core is language, and the computational methodologies facilitate communication between users and computers using natural language. A related term to machine conversation is the chatbot, a conversational agent that interacts with users turn by turn using natural language. Different chatbots or human-computer dialogue systems have been developed using text communication starting from ELIZA (Weizenbaum 1966) that simulates a psychotherapist , then PARRY (Colby 1973) which simulates a paranoid patient. " Colby regarded PARRY as a tool to study the nature of paranoia, and considered ELIZA as a potential clinical agent who could, within a time-sharing framework, autonomously handle several hundred patients an hour. " (Guzeldere and Franchi 1995). Nowadays a lot of chatbots are available online and are used for different purposes such as: MIA (MIA 2004) which is a German advisor on opening a bank account; and Sanelma (MUMMI 2004), a fictional female to talk with in a museum that provides information related to specific pieces of art. Practical applications and evaluation are key issues in Language Engineering: Cunningham (1999) characterises Language Engineering in terms of " …its focus on large-scale practical tasks and on quantitative evaluation of progress, and its willingness to embrace a diverse range of techniques ". The Loebner prize competition (Loebner 2003) has been used to evaluate machine conversation chatbots. The Loebner Prize is a Turing test, which evaluates the ability of the machine to fool people that they are talking to a human. In essence, judges