Papers
arxiv:1703.00607

Dynamic Word Embeddings for Evolving Semantic Discovery

Published on Mar 2, 2017
Authors:
,
,
,

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.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/1703.00607 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/1703.00607 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/1703.00607 in a Space README.md to link it from this page.

Collections including this paper 2