271 citations · 359 across the 8 of their papers we have counts for
5 papers · 1 filter
Discovering topics in text datasets by visualizing relevant words
Franziska Horn, Leila Arras, Grégoire Montavon +2
When dealing with large collections of documents, it is imperative to quickly get an overview of the texts' contents. In this paper we show how this can be achieved by using a clus…
Exploring text datasets by visualizing relevant words
Franziska Horn, Leila Arras, Grégoire Montavon +2
When working with a new dataset, it is important to first explore and familiarize oneself with it, before applying any advanced machine learning algorithms. However, to the best of…
Interactive Exploration and Discovery of Scientific Publications with PubVis
Franziska Horn
With an exponentially growing number of scientific papers published each year, advanced tools for exploring and discovering publications of interest are becoming indispensable. To…
Context encoders as a simple but powerful extension of word2vec
Franziska Horn
With a simple architecture and the ability to learn meaningful word embeddings efficiently from texts containing billions of words, word2vec remains one of the most popular neural…
Predicting Pairwise Relations with Neural Similarity Encoders
Franziska Horn, Klaus-Robert Müller
Matrix factorization is at the heart of many machine learning algorithms, for example, dimensionality reduction (e.g. kernel PCA) or recommender systems relying on collaborative fi…