Recent work has shown that deep generative models can assign higher likelihood to out-of-distribution data sets than to their training data [26,8]. We posit that this phenomenon is caused by a mismatch between the model's typical set and its areas of high probability density. In-distribution inputs should reside in the former but not necessarily in the latter, as previous work has presumed [6]. To determine whether or not inputs reside in the typical set, we propose a statistically principled, easy-to-implement test using the empirical distribution of model likelihoods. The test is model agnostic and widely applicable, only requiring that the likelihood can be computed or closely approximated. We report experiments showing that our procedure can successfully detect the out-of-distribution sets in several of the challenging cases reported by Nalisnick et al. [26].

This paper investigates the popular neural word embedding method Word2vec as a source of evidence in document ranking. In contrast to NLP applications of word2vec, which tend to use only the input embeddings, we retain both the input and the output embeddings, allowing us to calculate a different word similarity that may be more suitable for document ranking. We map the query words into the input space and the document words into the output space, and compute a relevance score by aggregating the cosine similarities across all the query-document word pairs. We postulate that the proposed Dual Embedding Space Model (DESM) provides evidence that a document is about a query term, in addition to and complementing the traditional term frequency based approach.

No abstract

Abstract-Automatic methods for analyzing sentiment and its movement through a play's social network are investigated. From structured dialogue we can algorithmically determine who is speaking and guess at who is listening or being directly addressed. Knowing who is speaking to whom allows the flow of sentiment to be tracked between characters and, within plays with clear time-lines, permits tracking the development of emotional relationships. We hypothesize that changing polarities between characters can be modeled as edge weights in a dynamic social network-a "sentiment network"-which can be used to distinguish a document's genre (tragedies versus comedies), detect a given character's enemies and allies, and model the overall emotional development of a play. Experiments on Shakespeare's plays are presented along with discussion of improvements and further applications.

The Bayesian paradigm has the potential to solve some of the core issues in modern deep learning, such as poor calibration, data inefficiency, and catastrophic forgetting. However, scaling Bayesian inference to the high-dimensional parameter spaces of deep neural networks requires restrictive approximations. In this paper, we propose performing inference over only a small subset of the model parameters while keeping all others as point estimates. This enables us to use expressive posterior approximations that would otherwise be intractable for the full model. In particular, we develop a practical and scalable Bayesian deep learning method that first trains a point estimate, and then infers a full covariance Gaussian posterior approximation over a subnetwork. We propose a subnetwork selection procedure which aims to optimally preserve posterior uncertainty. We empirically demonstrate the effectiveness of our approach compared to point-estimated networks and methods that use less expressive posterior approximations over the full network.