Eduardo M. Eisman

A Tool for Training Primary Health Care Medical Students: The Virtual Simulated Patient

In this paper we present an embodied conversational agent (ECA) that simulates a real human patient presenting several symptoms for training medical students in the field of primary health care. Students interview the ECA to diagnose his diseases as a doctor would do in a real situation. This virtual patient can communicate using natural language and express different moods that depend on the diseases he suffers from and the studentpsilas behavior. The ECApsilas behavior is done by means of the coordination of several modules devoted to different tasks: natural language understanding, dialogue management, emotional state control and natural language generation. An ontology that gathers the domain knowledge of the agent specifies a semantic language that the modules use to communicate themselves. The system has two kinds of advantages. First, it offers a way to put in practice the theoretical knowledge acquired by the students in their degree courses and to improve the diagnostic and communicative skills decreasing the learning curve of these abilities, setting them for an interview process like the one they are going to face in their real job. Second, the system is ready to use at any time without needing special or expensive equipment, only a standard PC.

Controlling the emotional state of an embodied conversationalagent with a dynamic probabilistic fuzzy rules based system

This paper presents an innovatory system for controlling the emotional state of an embodied conversational agent. Unlike other existing models, our system is fast adaptable to different application domains and it is highly interpretable. This will provide specialists with a tool to easily test their hypotheses about the most suitable emotional attitude for an agent in a specific domain. It also provides emotional stability and dynamic and automatic behavior orientation, which will result in the design of more believable conversational agents that behave as humans do.

Learning regular expressions to template-based FAQ retrieval systems

Template-based approaches have proven to be one of the most efficient and robustest ways of addressing Question Answering problems. Templates embody the experts knowledge on the domain and his/her ability to understand and answer questions, but designing these templates may become a complex task since it is usually carried out manually. Although these methods are not automatic, companies may prefer to undertake this solution in order to offer a better service. In this article, we propose a semiautomatic method to reduce the problem of creating templates to that of validate, and possibly modify, a list of proposed templates. In this way, a better trade-off between reliability-the system is still monitored by an expert-and cost is achieved. In addition, updating templates after domain changes becomes easier, human mistakes are reduced, and portability is increased. Our proposal is based on inferring regular expressions that induce the language conveyed by a set of previously collected query reformulations. The main contribution of this work consists of the definition of a suitable optimisation measure that effectively reflects some important aspects of the problem and the theoretical soundness that supports it.

A framework for designing closed domain virtual assistants

Highlights? Virtual assistant framework that helps users find useful information in a website. ? It engages users in conversation using natural language, as real assistants. ? Users can omit some words if they are implicit in the conversation (context). ? It answers peoples questions and offer related information of the highest interest. ? It is multilingual and can be integrated into every existing website. Since its beginning in 1969, the Internet has grown rapidly, especially over the past few years. Companies and organizations store more and more information about themselves on the Internet. Sometimes, that information is not well organized. Other times, the huge volume of available data makes useful information difficult to be found. The result is that users have to waste their time looking for what they want to know using the traditional menu-driven navigation and keyword search that websites provide. This is a critical issue because it decreases users interest about companies. In order to avoid this problem, in this paper we propose a framework for designing virtual assistants, which are, considering first results, an ideal alternative to help users find, not only the information that they are looking for, but also some related information which could be of the highest interest.

A multi-agent conversational system with heterogeneous data sources access

We present a multi-agent conversational architecture for heterogeneous data sources.Expert agents are specialized in accessing different knowledge sources.Decision agents coordinate expert agents to provide a coherent final answer to users.This generic architecture is used to make a SmartSeller for a bookstore.A comparative analysis demonstrates several improvements regarding existing systems. In many of the problems that can be found nowadays, information is scattered across different heterogeneous data sources. Most of the natural language interfaces just focus on a very specific part of the problem (e.g. an interface to a relational database, or an interface to an ontology). However, from the point of view of users, it does not matter where the information is stored, they just want to get the knowledge in an integrated, transparent, efficient, effective, and pleasant way. To solve this problem, this article proposes a generic multi-agent conversational architecture that follows the divide and conquer philosophy and considers two different types of agents. Expert agents are specialized in accessing different knowledge sources, and decision agents coordinate them to provide a coherent final answer to the user. This architecture has been used to design and implement SmartSeller, a specific system which includes a Virtual Assistant to answer general questions and a Bookseller to query a book database. A deep analysis regarding other relevant systems has demonstrated that our proposal provides several improvements at some key features presented along the paper.