An Agent-Based Dialog Simulation Technique to Develop and Evaluate Conversational Agents
نویسندگان
چکیده
In this paper, we present an agent-based dialog simulation technique for learning new dialog strategies and evaluate conversational 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 compare different dialog corpora. We have applied this technique to explore the space of possible dialog strategies and evaluate the dialogs acquired for a conversational agent that collects monitored data from patients suffering from diabetes.
منابع مشابه
Agent Simulation to Develop Interactive and User-Centered Conversational Agents
In this paper, we present a technique for developing user simulators which are able to interact and evaluate conversational agents. Our technique is based on a statistical model that is automatically learned from a dialog corpus. This model is used by the user simulator to provide the following answer taking into account the complete history of the interaction. The main objective of our proposa...
متن کاملAn Automatic Dialog Simulation Technique to Develop and Evaluate Interactive Conversational Agents
متن کامل
The Enhanced Arabchat: An Arabic Conversational Agent
The Enhanced ArabChat is a complement of the previous version of ArabChat. This paper details an enhancements development of a novel and practical Conversational Agent for the Arabic language called the “Enhanced ArabChat”. A conversational Agent is a computer program that attempts to simulate conversations between machine and human. Some of lessons was learned by evaluating the previous work o...
متن کاملLangage de conversation multimodal pour agent conversationnel animé
This article falls within the realm of dialogue between a human and an Embodied Conversational Agent (ECA). We claim that a specific agent conversational language is needed for such interactions, based on the essential role of emotion in human communication. In order to define this language, we propose a library of Multimodal Conversation Acts is proposed, based in particular on speech acts and...
متن کاملGradual probabilistic DFA learning with caching for conversational agents
SUMMARY This paper proposes a method of reducing the cost of gradually constructing task-oriented conversational agents with FSMs by collecting example dialogues. Probabilistic-DFA learning algorithms with the state merging method are available for the FSM-based dialogue model. However, these algorithms must learn the whole model again as often as the example data increase. We proposed a learni...
متن کامل