In this paper, we propose a self-learning architecture for generating natural language templates for conversational assistants.Generating templates to cover all the combinations of slots in an intent is time consuming and labor-intensive.We examine three different models based on our proposed architecture -Rule-based model, Sequence-to-Sequence (Seq2Seq) model and Semantically Conditioned LSTM (SC-LSTM) model for the IoT domain -to reduce the human labor required for template generation.We demonstrate the feasibility of template generation for the IoT domain using our self-learning architecture.In both automatic and human evaluation, the self-learning architecture outperforms previous works trained with a fully human-labeled dataset.This is promising for commercial conversational assistant solutions.

In this poster, we propose an emotion analysis method using context information gathered from sensor data. We observe that there are certain situations in which a specific emotion is strongly felt, i.e. dominant. We develop a "scenario-based" approach that focuses on creating such situations with dominant emotion, using a set of context information from sensor data. These "scenarios" undergo validation process through a preliminary survey. Finally, an application prototype detects these scenarios to return the analyzed emotion to the user.