TY  - JOUR
T1  - Korean Movie Review Sentiment Analysis using Self-Attention and Contextualized Embedding
AU  - Park, Cheoneum 
AU  - Lee, Dongheon 
AU  - Kim, Kihoon 
AU  - Lee, Changki 
AU  - Kim, Hyunki 
JO  - Journal of KIISE, JOK
PY  - 2019
DA  - 2019/1/14
DO  - 10.5626/JOK.2019.46.9.901
KW  - Self-Attention
KW  - RNN
KW  - Sentiment analysis
KW  - movie review
KW  - contextualized embedding
AB  - Sentiment analysis is the processing task that involves collecting and classifying opinions about a specific object. However, it is difficult to grasp the subjectivity of a person using natural language, so the existing sentimental word dictionaries or probabilistic models cannot solve such a task, but the development of deep learning made it possible to solve the task. Self-attention is a method of modeling a given input sequence by calculating the attention weight of the input sequence itself and constructing a context vector with a weighted sum. In the context, a high weight is calculated between words with similar meanings. In this paper, we propose a method using a modeling network with self-attention and pre-trained contextualized embedding to solve the sentiment analysis task. The experimental result shows an accuracy of 89.82%.