26 datasets found

Hierarchical Dirichlet Process (HDP) mixture model for modeling the hierarchy of groups of data.

The NOISE dataset is a semi-synthetic dataset constructed from the matrix A∗, where the data is generated from y = A∗x + ζ, where ζ is the noise.

The NEG dataset is a semi-synthetic dataset constructed from the matrix A∗, where the entries of A∗ are i.i.d. samples from the uniform distribution on [−0.5, 0.5).

The CTM dataset is a semi-synthetic dataset constructed from the matrix X, whose columns are drawn from the logistic normal prior in the correlated topic model.

The DIR dataset is a semi-synthetic dataset constructed from the matrix X, whose columns are from a Dirichlet distribution with parameters (0.05, 0.05,..., 0.05).

NIPS dataset is used to test the proposed Hierarchical Latent Word Clustering algorithm.

The dataset consists of 300 topics generated using Wikipedia articles and news articles taken from the New York Times. Each topic is represented by ten terms with the highest...

The Search Snippets dataset is a collection of search snippets from Google.

The Pascal Flickr dataset is a collection of captions for images from Flickr.

The dataset used in this paper is a collection of short texts, including tweets, Pascal Flickr captions, and search snippets.

Enrico: A dataset for topic modeling of mobile UI designs

The dataset used in the paper is the New York Times dataset and the 20Newsgroups dataset.

The 20Newsgroups data set is a dataset of 18,846 instances of newsgroup documents.

The Japanese election manifesto data contains texts of Japanese election manifestos.

The Congressional bills project dataset contains texts of congressional bills.

The paper discusses the use of multi-objective Bayesian optimization for hyperparameter transfer in topic models.

The paper discusses the use of multi-objective Bayesian optimization for hyperparameter transfer in topic models.

The paper discusses the use of multi-objective Bayesian optimization for hyperparameter transfer in topic models.

The Graphbtm dataset is a biterm topic model.

The RCV1 dataset is a corpus of Reuters news articles.