The recent explosion in work on neural topic modeling has been criticize...
Pretraining is the preliminary and fundamental step in developing capabl...
Selecting a birth control method is a complex healthcare decision. While...
Transformers allow attention between all pairs of tokens, but there is r...
Explainable question answering systems should produce not only accurate
...
Across many data domains, co-occurrence statistics about the joint appea...
We explore Boccaccio's Decameron to see how digital humanities tools can...
Much of the progress in contemporary NLP has come from learning
represen...
Images can give us insights into the contextual meanings of words, but
c...
Clustering token-level contextualized word representations produces outp...
In this article we describe our experiences with computational text anal...
Images and text co-occur everywhere on the web, but explicit links betwe...
Multimodal machine learning algorithms aim to learn visual-textual
corre...
Spectral topic modeling algorithms operate on matrices/tensors of word
c...
The anchor words algorithm performs provably efficient topic model infer...
The content of today's social media is becoming more and more rich,
incr...
Spectral inference provides fast algorithms and provable optimality for
...
Topic models provide a useful method for dimensionality reduction and
ex...
We present a hybrid algorithm for Bayesian topic models that combines th...
A database of objects discovered in houses in the Roman city of Pompeii
...