Papers

The social interaction between librarian and patron that occurs in the traditional library setting is a unique and important component of the services that libraries provide. With more services moving online, libraries face the challenge of providing a friendly, socially rich environment for their online users. Using interface agent technology could be one way to make online library services more socially engaging. Read more

We are developing an ECA (Embodied Communicational Agent) system in Hungarian language. The ECA has to be able to carry out general chat conversations and domain specific discussions as well. The structure of the dialogue graph and the attributes of the graph nodes have to support the success of the conversation: user utterance understanding and responding, as well as repairing the “non-understanding” situations. In the following sections we are briefly depicting the system and describe... Read more

The paper describes the BotCom complex embedded conversational agent system, which is accessible over the Internet and capable of high quality natural language processing as well as sophisticated manipulation of emotions. It relies on an extension of Plutchik’s emotional model. Experimental cases leading to useful constraints for optimization are discussed. BotCom, a prototype for a robust commercial application, is the outcome of both research and realistic development. Read more

Chatterbots are computer programs that simulate intelligent conversation. They make use of various techniques such as pattern matching, indexing, sentence reconstruction, and even natural language processing. In this paper we present an approach to chatterbots that mixes pattern matching with indexing and query matching methods inspired from information retrieval. We propose a model in which new sentences can be produced from existing ones using an evolutionary algorithm adapted to the structure of the natural language. Read more

What many AI researchers do when they say they are doing AI contradicts what some AI researchers say is AI. Surveys of leading AI textbooks demonstrate a lack of a generally accepted historical record. These surveys also show AI researchers as primarily concerned with prescribing ideal mathematical behaviors into computers - accounting for 987 of 996 (or 99%) of the AI references surveyed. The most common expectation of AI concerns constructing machines that behave like... Read more

The ethical issues related to the possible future creation of machines with general intellectual capabilities far outstripping those of humans are quite distinct from any ethical problems arising in current automation and information systems. Such superintelligence would not be just another technological development; it would be the most important invention ever made, and would lead to explosive progress in all scientific and technological fields, as the superintelligence would conduct research with superhuman efficiency.... Read more

AIML - A recently developed standard for describing knowledge for Robots using XML data structures is introduced. A very large English-based robot knowledge base developed using the standard is described. Many other knowledge-based projects based on other international languages are described. The English-based knowledge base is currently interacting with people at a rate of 100,000 inquiries per day. A unique web-based computer architecture (http://www.pandorabots.com) supporting the on-going development of the knowledge base is described. The... Read more

We discuss how simulating emotional dialogs with an Embodied Agent requires endowing it with ability to manifest appropriately emotions but also to exploit them in controlling behavior. We then describe a domain-independent testbed to simulate dialogs in affective domains and verify how they change when the context in which interaction occurs is varied. Emotion activation is simulated by dynamic belief networks while dialog simulation is implemented within a logical framework. Read more

This paper presents a pilot study involving 99 participants analysing conversations between Judges 2, 4 and 7, hidden humans (Confederates), and Jabberwock, bronze prize winner for most human-like machine from Loebner’s 2003 Contest, instantiation of Turing’s Test for machine intelligence. The transcripts from these conversations were given to children (aged between 8 and 12), and adults (aged between 18-35). The machine was identified in its conversation with Judge 7, but the Confederate Effect featured in... Read more

The notion of trust has been virtually absent from most work on how people assess and choose their information sources. Based on two empirical cases this study shows that software engineers and users of e-commerce websites devote a lot of attention to considerations about the trustworthiness of their sources, which include people, documents, and virtual agents. In the project-based software engineering environment trust tends to be a collaborative issue and the studied software engineers normally... Read more