Michael Gill


Conditional Word Embedding and Hypothesis Testing via Bayes-by-Backprop
Rujun Han | Michael Gill | Arthur Spirling | Kyunghyun Cho
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Conventional word embedding models do not leverage information from document meta-data, and they do not model uncertainty. We address these concerns with a model that incorporates document covariates to estimate conditional word embedding distributions. Our model allows for (a) hypothesis tests about the meanings of terms, (b) assessments as to whether a word is near or far from another conditioned on different covariate values, and (c) assessments as to whether estimated differences are statistically significant.