JCSE, vol. 16, no. 3, pp.165-177, 2022

DOI: http://dx.doi.org/10.5626/JCSE.2022.16.3.165

Low-Dimensional Vector Representation Learning for Text Visualization Using Task-Oriented Dialogue Dataset

Taewook Hwang, Sangkeun Jung and Yoon-Hyung Roh
Computer Science & Engineering, Chungnam National University, Daejeon, Korea Language Intelligence Research Lab., Electronics and Telecommunications Research Institute, Daejeon, Korea

Abstract: Text visualization is a complex technique that helps in data understanding and insight, and may lead to loss of information. Through the proposed low-dimensional vector representation learning method, deep learning and visualization through low-dimensional vector space construction were simultaneously performed. This method can transform a taskoriented dialogue dataset into low-dimensional coordinates, and based on this, a deep learning vector space can be constructed. The low-dimensional vector representation deep learning model found the intent of a sentence within a dataset and predicted the sentence components well in 3 out of 5 datasets. In addition, by checking the prediction results in the low-dimensional vector space, it was possible to improve the understanding of the data, such as identifying the structure or errors in the data.

Keyword: Natural language processing; Natural language understanding; Vector representation learning; Text visualization; Task-oriented dialogue dataset

Full Paper:   153 Downloads, 591 View