TY  - JOUR
T1  - Regularizing Korean Conversational Model by Applying Denoising Mechanism
AU  - Kim, Tae-Hyeong 
AU  - Noh, Yunseok 
AU  - Park, Seong-Bae 
AU  - Park, Se-Yeong 
JO  - Journal of KIISE, JOK
PY  - 2018
DA  - 2018/1/14
DO  - 10.5626/JOK.2018.45.6.572
KW  - conversational model
KW  - sequence-to-sequence model
KW  - natural language generation
KW  - regularization
AB  - A conversation system is a system that responds appropriately to input utterances. Recently, the sequence-to-sequence framework has been widely used as a conversation-learning model. However, the conversation model learned in such a way often generates a safe and dull response that does not provide appropriate information or sophisticated meaning. In addition, this model is also useless for input utterances appearing in various forms, such as with changed ending words or changed word order. To solve these problems, we propose a denoising response generation model applying a denoising mechanism. By injecting noise into original input, the proposed method creates a model that will stochastically experience new input made up of items that were not included in the original data during the training process. This data augmentation effect regularizes the model and allows the realization of a robust model. We evaluate our model using 90k input utterances-responses from Korean conversation pair data. The proposed model achieves better results compared to a baseline model on both ROUGE F1 score and qualitative evaluations by human annotators.