Improving Classification-Based Natural Language Understanding with Non-Expert Annotation
Fabrizio Morbini, Eric Forbell, Kenji Sagae · 2014
Although data-driven techniques are com-monly used for Natural Language Under-standing in dialogue systems, their effi-cacy is often hampered by the lack of ap-propriate annotated training data in suffi-cient amounts. We present an approach for rapid and cost-effective annotation of training data for classification-based lan-guage understanding in conversational di-alogue systems. Experiments using a web-accessible conversational character that in-teracts with a varied user population show that a dramatic improvement in natural language understanding and a substantial reduction in expert annotation effort can be achieved by leveraging non-expert an-notation.