Dynamic Word Embeddings for Evolving Semantic Discovery

Abstract

Word evolution refers to the changing meanings and associations of words throughout time, as a byproduct of human language evolution. By studying word evolution, we can infer social trends and language constructs over different periods of human history. However, traditional techniques such as word representation learning do not adequately capture the evolving language structure and vocabulary. In this paper, we develop a dynamic statistical model to learn time-aware word vector representation. We propose a model that simultaneously learns time-aware embeddings and solves the resulting "alignment problem". This model is trained on a crawled NYTimes dataset. Additionally, we develop multiple intuitive evaluation strategies of temporal word embeddings. Our qualitative and quantitative tests indicate that our method not only reliably captures this evolution over time, but also consistently outperforms state-of-the-art temporal embedding approaches on both semantic accuracy and alignment quality.

arXiv comment9 pages, published in the International Conference on Web Search and Data Mining (WSDM 2018)

Cited by in corpus (8)

• Dynamic Language Models for Continuously Evolving Content
• Learning Backward Compatible Embeddings
• VideoMap: Supporting Video Editing Exploration, Brainstorming, and Prototyping in the Latent Space
• Learning Dynamic Author Representations with Temporal Language Models
• Diachronic Cross-modal Embeddings
• Visualizing Temporal Topic Embeddings with a Compass
• Measuring Psychological Constructs from Social Media Text Using the Word Embedding Projection Approach
• Subdiffusive semantic evolution in Indo-European languages