An Automatic Dialog Simulation Technique to Develop and Evaluate Interactive Conversational Agents

Abstract

During recent years, conversational agents have become a solution to provide straightforward and more natural ways of retrieving information in the digital domain. In this article, we present an agent based dialog simulation technique for learning new dialog strategies and evaluating con versational agents. Using this technique, the effort necessary to acquire data required to train the dialog model and then explore new dialog strategies is considerably reduced. A set of measures has also been defined to evaluate the dialog strategy that is automatically learned and to compare different dialog corpora. We have applied this technique to explore the space of possible dialog stra tegies and evaluate the dialogs acquired for a conversational agent that collects monitored data from patients suffering from diabetes. The results of the comparison of these measures for an initial corpus and a corpus acquired using the dialog simulation technique show that the conversational agent reduces the time needed to complete the dialogs and improve their quality, thereby allowing the conversational agent to tackle new situations and generate new coherent answers for the situations already present in an initial model.

A Proposal for Processing and Fusioning Multiple Information Sources in Multimodal Dialog Systems

“…The dialog manager receives EMMA files containing the results processed by the modules that deal with each input modality. As in our previous work on user modeling and dialog management [21,11], we propose the definition of a data structure to store the values for the different concepts and attributes provided by means of the different input modalities along the dialog history.…”

“…The statistical technique that we propose to model user's intention is described in [21]. The proposed technique carries out the functions of the ASR and SLU modules, i.e., it estimates user's intention providing the semantic interpretation of the user utterance in the same format defined for the output of the SLU module.…”

A Framework to Develop Adaptive Multimodal Dialog Systems for Android-Based Mobile Devices

“…As in our previous work on user modeling and dialog management [11], we propose the definition of a data structure similar to the User Register to store the values for the different concepts and attributes provided by means of the different input modalities along the dialog history, which we called Interaction Register (IR).…”

“…The statistical technique that we propose to model user's intention is described in [11]. The proposed technique carries out the functions of the ASR and SLU modules, i.e., it estimates user's intention providing the semantic interpretation of the user utterance in the same format defined for the output of the SLU module.…”

“…The statistical models for the user's intention recognizer and dialog management modules were learned using a corpus acquired by means of an automatic dialog generation technique previously developed [13]. The application also allows users to complete a profile corresponding to their preferences on the location of the initial maps, preferred travel facilities, preferred types of stores, and specific details for each one of them.…”