Search Results for author:
Found 4 papers, 1 papers with code
Neural Dynamic Focused Topic Model
Topic models and all their variants analyse text by learning meaningful representations through word co-occurrences.
The future is different: Large pre-trained language models fail in prediction tasks
Our models display performance drops of only about 40% in the worst cases (2% in the best ones) when predicting the popularity of future posts, while using only about 7% of the total number of parameters of LPLM and providing interpretable representations that offer insight into real-world events, like the GameStop short squeeze of 2021
Hidden Schema Networks
Large, pretrained language models infer powerful representations that encode rich semantic and syntactic content, albeit implicitly.
Recurrent Adversarial Service Times
Service system dynamics occur at the interplay between customer behaviour and a service provider's response.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
