Users in consumption domains, like music, are often able to more efficie...
Conversational recommendation systems (CRSs) enable users to use natural...
Language models (LMs) now excel at many tasks such as few-shot learning,...
Many important questions (e.g. "How to eat healthier?") require conversa...
Pretrained (language) embeddings are versatile, task-agnostic feature
re...
To understand a sentence like "whereas only 10
below the poverty line, 2...
For evaluating generation systems, automatic metrics such as BLEU cost
n...
How much is 131 million US dollars? To help readers put such numbers in
...
Mixture modeling is a general technique for making any simple model more...
Tensor factorization arises in many machine learning applications, such
...
Discriminative latent-variable models are typically learned using EM or
...