Dynamic Word Embeddings for Evolving Semantic Discovery
This addresses the challenge of modeling word evolution for applications in social trend analysis and historical linguistics, representing an incremental improvement over existing temporal embedding approaches.
The paper tackles the problem of capturing evolving word meanings over time by developing a dynamic statistical model for time-aware word embeddings, which outperforms state-of-the-art methods on semantic accuracy and alignment quality.
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.