Domain-Adaptive Conversational Agent with Two-Stage Dialogue Management
نویسندگان
چکیده
The conversational agent understands and provides users with proper information based on natural language. Conventional agents based on pattern matching have many restrictions to manage various types of real dialogues and to improve the answering performance. For the effective construction of conversational agents, we propose a domain-adaptive conversational agent that infers the user’s intention with two-stage inference and incrementally improves the answering performance through a learning dialogue. We can confirm the usefulness of the proposed method with illustrations and usability tests.
منابع مشابه
A Two-Stage Bayesian Network for Effective Development of Conversational Agent
Conversational agent is a system that provides user with proper information and maintains the context of dialogue based on natural language. When experts design the network for conversational agent of a domain, the network is usually very complicated and is hard to be understood. So the simplification of network by separating variables in the domain is helpful to design the conversational agent...
متن کاملOptimizing Situated Dialogue Management in Unknown Environments
We present a conversational learning agent that helps users navigate through complex and challenging spatial environments. The agent exhibits adaptive behaviour by learning spatiallyaware dialogue actions while the user carries out the navigation task. To this end, we use Hierarchical Reinforcement Learning with relational representations to efficiently optimize dialogue actions tightly-coupled...
متن کامل"How about this weather?" Social Dialogue with Embodied Conversational Agents
Social dialogue can be used by an embodied interface agent both to satisfy "interpersonal" goals, such as building rapport with the user and demonstrating the expertise of the agent, and to directly or indirectly satisfy task goals, such as acquiring background information about the user. We describe the ongoing development of an embodied conversational agent that is capable of multimodal input...
متن کاملChallenges for Adaptive Conversational Agents
State-of-the-art dialogue technology has reached a level that allows its use in commercial applications, enabling users to have short conversations with the system to search for information. However, the unique requirements that arise from the combination of system knowledge representation, interaction management, and interface design have to be addressed as part of the system development proce...
متن کاملJoint Identification and Segmentation of Domain-Specific Dialogue Acts for Conversational Dialogue Systems
Individual utterances often serve multiple communicative purposes in dialogue. We present a data-driven approach for identification of multiple dialogue acts in single utterances in the context of dialogue systems with limited training data. Our approach results in significantly increased understanding of user intent, compared to two strong baselines.
متن کامل