Learning Dynamic Author Representations with Temporal Language Models
This work addresses the need for dynamic author representations in text mining and information retrieval, offering an incremental improvement by incorporating temporal and author information into existing language models.
The paper tackles the problem of language models ignoring author identities and publication dates by proposing a neural model that conditions on author and temporal states to capture language diffusion in author communities over time. The result is beating several baselines on two real-world corpora and learning meaningful time-varying author representations.
Language models are at the heart of numerous works, notably in the text mining and information retrieval communities. These statistical models aim at extracting word distributions, from simple unigram models to recurrent approaches with latent variables that capture subtle dependencies in texts. However, those models are learned from word sequences only, and authors' identities, as well as publication dates, are seldom considered. We propose a neural model, based on recurrent language modeling, which aims at capturing language diffusion tendencies in author communities through time. By conditioning language models with author and temporal vector states, we are able to leverage the latent dependencies between the text contexts. This allows us to beat several temporal and non-temporal language baselines on two real-world corpora, and to learn meaningful author representations that vary through time.