The end-to-end performance of natural language processing systems for compound tasks, such as question answering and textual entailment, is often hampered by use of a greedy 1-bes...
Jenny Rose Finkel, Christopher D. Manning, Andrew ...
This study stems from a suggestion in the literature (Lohse and Spiller, 1999) that for some products an increase in the amount of information presented on a web site has a negati...
Forecasting is of prime importance for accuracy in decision making. For data sets containing high autocorrelations, failure to account for temporal dependence will result in poor ...
Abstract. We study the problem of multimodal dimensionality reduction assuming that data samples can be missing at training time, and not all data modalities may be present at appl...
Discrete mixed membership modeling and continuous latent factor modeling (also known as matrix factorization) are two popular, complementary approaches to dyadic data analysis. In...