Learning document embeddings along with their uncertainties

Abstract

Majority of the text modelling techniques yield only point-estimates of document embeddings and lack in capturing the uncertainty of the estimates. These uncertainties give a notion of how well the embeddings represent a document. We present Bayesian subspace multinomial model (Bayesian SMM), a generative log-linear model that learns to represent documents in the form of Gaussian distributions, thereby encoding the uncertainty in its covariance. Additionally, in the proposed Bayesian SMM, we address a commonly encountered problem of intractability that appears during variational inference in mixed-logit models. We also present a generative Gaussian linear classifier for topic identification that exploits the uncertainty in document embeddings. Our intrinsic evaluation using perplexity measure shows that the proposed Bayesian SMM fits the data better as compared to the state-of-the-art neural variational document model on (Fisher) speech and (20Newsgroups) text corpora. Our topic identification experiments show that the proposed systems are robust to over-fitting on unseen test data. The topic ID results show that the proposed model is outperforms state-of-the-art unsupervised topic models and achieve comparable results to the state-of-the-art fully supervised discriminative models.

Rethinking the Objectives of Extractive Question Answering

“…To represent passages, we have used Bayesian subspace multinomial model (BSMM) (Kesiraju et al, 2019). BSMM is generative log-linear model that learns to represent passages in the form of Gaussian distributions and achieves state-of-the-art results in topic identification.…”