Compressing and interpreting word embeddings with latent space regularization and interactive semantics probing

• Published in: Information visualization Vol. 22; no. 1; pp. 52 - 68
• Main Authors: Li, Haoyu, Wang, Junpeng, Zheng, Yan, Wang, Liang, Zhang, Wei, Shen, Han-Wei
• Format: Journal Article
• Language: English
• Published: London, England SAGE Publications 01.01.2023; SAGE PUBLICATIONS, INC
• Subjects: Compressing; Embedding; Machine learning; Natural language processing; Photovoltaic cells; Regularization; Representations; Semantics; Words (language); visual analytics; word embedding; High-dimensional data visualization; neural networks

Word embedding, a high-dimensional (HD) numerical representation of words generated by machine learning models, has been used for different natural language processing tasks, for example, translation between two languages. Recently, there has been an increasing trend of transforming the HD embedding...