Building Brownian Bridges to Learn Dynamic Author Representations from Texts
Published in Advances in Intelligent Data Analysis XXII, IDA 2024, 2024
This article introduces BARL, a new model using Brownian Bridges to learn dynamic embeddings of authors. Each document is a point in the latent space, and each author is seen as a trajectory evolving through time.
Recommended citation:Terreau, E., Velcin, J. (2024). Building Brownian Bridges to Learn Dynamic Author Representations from Texts. In: Miliou, I., Piatkowski, N., Papapetrou, P. (eds) Advances in Intelligent Data Analysis XXII. IDA 2024. Lecture Notes in Computer Science, vol 14641. Springer, Cham.