David Mimno

Pulling Out the Stops: Rethinking Stopword Removal for Topic Models

2017

It is often assumed that topic models benefit from the use of a manually curated stopword list. Constructing this list is timeconsuming and often subject to user judgments about what kinds of words are important …

Evaluation methods for unsupervised word embeddings

2015

We present a comprehensive study of evaluation methods for unsupervised embedding techniques that obtain meaningful representations of words from text. Different evaluations result in different orderings of embedding methods, calling into question the common assumption …

The strange geometry of skip-gram with negative sampling

2017

Despite their ubiquity, word embeddings trained with skip-gram negative sampling (SGNS) remain poorly understood. We find that vector positions are not simply determined by semantic similarity, but rather occupy a narrow cone, diametrically opposed to …