A method of mining the change of word semantic across different timescales
Download as PDF
Maoyuan Zhang, Shuyuan Sun, Yibo Wang
Language evolves over time, and language changes its meaning due to cultural changes, technological inventions, or political events. Language variation and change is an important branch of sociolinguistics and has achieved remarkable achievements. But there is seldom study conducted from the aspect of the natural language processing. In this paper, we propose a probabilistic language model of timestamp text data, which can track the semantic evolution of a single word over time and use the cloud model to compute the change of words. Experiments show that the proposed method has good semantic information and useful results in semantic change and change analysis.
Word variation, Word embeddings, Cloud model.