Learning situated knowledge bases through dialog
نویسندگان
چکیده
To respond to a user’s query, dialog agents can use a knowledge base that is either domain specific, commonsense (e.g., NELL, Freebase) or a combination of both. The drawback is that domain-specific knowledge bases will likely be limited and static; commonsense ones are dynamic but contain general information found on the web and will be sparse with respect to a domain. We address this issue through a system that solicits situational information from its users in a domain that provides information on events (seminar talks) to augment its knowledge base (covering an academic field). We find that this knowledge is consistent and useful and that it provides reliable information to users. We show that, in comparison to a base system, users find that retrievals are more relevant when the system uses its informally acquired knowledge to augment their queries.
منابع مشابه
Learning Grounded Language through Situated Interactive Instruction
We present an approach for learning grounded language from mixed-initiative human-robot interaction. Prior work on learning from human instruction has concentrated on acquisition of task-execution knowledge from domainspecific language. In this work, we demonstrate acquisition of linguistic, semantic, perceptual, and procedural knowledge from mixed-initiative, natural language dialog. Our appro...
متن کاملKnowledge Discovery Through Spoken Dialog
People can acquire knowledge not only from media such as books, but also through interactions with other people. Automated dialog agents, however, typically limit their learning from labeled data, and programming. This thesis describes an approach that enables such agents to actively acquire new knowledge through spoken dialog interaction. To acquire knowledge in different situations, we propos...
متن کاملAIED 2013 Workshops Proceedings
In this paper, I bring out the contrasts between two different approaches to student learning: that of computational learning scientists and socio-cultural anthropologists, and suggest some implications and directions for learning research in MOOCs. Computational learning scientists see learning as a matter of imbibing particular knowledge propositions, and therefore understand teaching as a wa...
متن کاملTwo Models of Learning: Cognition Vs. Socialization
In this paper, I bring out the contrasts between two different approaches to student learning: that of computational learning scientists and socio-cultural anthropologists, and suggest some implications and directions for learning research in MOOCs. Computational learning scientists see learning as a matter of imbibing particular knowledge propositions, and therefore understand teaching as a wa...
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