Abstract | ||
---|---|---|
When developing a conversational agent, there is often an urgent need to have a prototype available in order to test the application with real users. A Wizard of Oz is a possibility, but sometimes the agent should be simply deployed in the environment where it will be used. Here, the agent should be able to capture as many interactions as possible and to understand how people react to failure. In this paper, we focus on the rapid development of a natural language understanding module by non experts. Our approach follows the learning paradigm and sees the process of understanding natural language as a classification problem. We test our module with a conversational agent that answers questions in the art domain. Moreover, we show how our approach can be used by a natural language interface to a cinema database. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1007/978-3-642-23974-8_33 | IVA'11 Proceedings of the 10th international conference on Intelligent virtual agents |
Keywords | DocType | Volume |
natural language interface,real user,rapid development,conversational agent,cinema database,non expert,classification problem,natural language,natural language understanding module,art domain | Journal | abs/1302.1380 |
ISSN | Citations | PageRank |
In Proceedings of the 11th International Conference on Intelligent
Virtual Agents, 2011 | 6 | 0.63 |
References | Authors | |
7 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Catarina Moreira | 1 | 52 | 8.90 |
Ana Cristina Mendes | 2 | 93 | 11.59 |
Luísa Coheur | 3 | 199 | 34.38 |
Bruno Martins | 4 | 441 | 34.58 |