University of Massachusetts Amherst

About: University of Massachusetts Amherst is a education organization based out in Amherst Center, Massachusetts, United States. It is known for research contribution in the topics: Population & Galaxy. The organization has 37274 authors who have published 83965 publications receiving 3834996 citations. The organization is also known as: UMass Amherst & Massachusetts State College.

Deep contextualized word representations

Abstract: We introduce a new type of deep contextualized word representation that models both (1) complex characteristics of word use (e.g., syntax and semantics), and (2) how these uses vary across linguistic contexts (i.e., to model polysemy). Our word vectors are learned functions of the internal states of a deep bidirectional language model (biLM), which is pre-trained on a large text corpus. We show that these representations can be easily added to existing models and significantly improve the state of the art across six challenging NLP problems, including question answering, textual entailment and sentiment analysis. We also present an analysis showing that exposing the deep internals of the pre-trained network is crucial, allowing downstream models to mix different types of semi-supervision signals.

Generating Sentences from a Continuous Space

Abstract: The standard recurrent neural network language model (RNNLM) generates sentences one word at a time and does not work from an explicit global sentence representation. In this work, we introduce and study an RNN-based variational autoencoder generative model that incorporates distributed latent representations of entire sentences. This factorization allows it to explicitly model holistic properties of sentences such as style, topic, and high-level syntactic features. Samples from the prior over these sentence representations remarkably produce diverse and well-formed sentences through simple deterministic decoding. By examining paths through this latent space, we are able to generate coherent novel sentences that interpolate between known sentences. We present techniques for solving the difficult learning problem presented by this model, demonstrate its effectiveness in imputing missing words, explore many interesting properties of the model's latent sentence space, and present negative results on the use of the model in language modeling.

Ultrahydrophobic surfaces. Effects of topography length scales on wettability

Abstract: We discuss dynamic hydrophobicity from the perspective of the force required to move a water droplet on a surface and argue that the structure of the three-phase contact line is important. We studied the wettability of a series of silicon surfaces that were prepared by photolithography and hydrophobized using silanization reagents. Hydrocarbon, siloxane, and fluorocarbon surfaces were prepared. The surfaces contain posts of different sizes, shapes, and separations. Surfaces containing square posts with X−Y dimensions of 32 μm and less exhibited ultrahydrophobic behavior with high advancing and receding water contact angles. Water droplets moved very easily on these surfaces and rolled off of slightly tilted surfaces. Contact angles were independent of the post height from 20 to 140 μm and independent of surface chemistry. Water droplets were pinned on surfaces containing square posts with larger dimensions. Increasing the distance between posts and changing the shape of the posts from square to staggered ...

A comparison of goodness-of-fit tests for the logistic regression model.

Abstract: Recent work has shown that there may be disadvantages in the use of the chi-square-like goodness-of-fit tests for the logistic regression model proposed by Hosmer and Lemeshow that use fixed groups of the estimated probabilities. A particular concern with these grouping strategies based on estimated probabilities, fitted values, is that groups may contain subjects with widely different values of the covariates. It is possible to demonstrate situations where one set of fixed groups shows the model fits while the test rejects fit using a different set of fixed groups. We compare the performance by simulation of these tests to tests based on smoothed residuals proposed by le Cessie and Van Houwelingen and Royston, a score test for an extended logistic regression model proposed by Stukel, the Pearson chi-square and the unweighted residual sum-of-squares. These simulations demonstrate that all but one of Royston's tests have the correct size. An examination of the performance of the tests when the correct model has a quadratic term but a model containing only the linear term has been fit shows that the Pearson chi-square, the unweighted sum-of-squares, the Hosmer-Lemeshow decile of risk, the smoothed residual sum-of-squares and Stukel's score test, have power exceeding 50 per cent to detect moderate departures from linearity when the sample size is 100 and have power over 90 per cent for these same alternatives for samples of size 500. All tests had no power when the correct model had an interaction between a dichotomous and continuous covariate but only the continuous covariate model was fit. Power to detect an incorrectly specified link was poor for samples of size 100. For samples of size 500 Stukel's score test had the best power but it only exceeded 50 per cent to detect an asymmetric link function. The power of the unweighted sum-of-squares test to detect an incorrectly specified link function was slightly less than Stukel's score test. We illustrate the tests within the context of a model for factors associated with low birth weight.

ConSurf 2010: calculating evolutionary conservation in sequence and structure of proteins and nucleic acids

Abstract: It is informative to detect highly conserved positions in proteins and nucleic acid sequence/structure since they are often indicative of structural and/or functional importance. ConSurf (http://consurf.tau.ac.il) and ConSeq (http://conseq.tau.ac.il) are two well-established web servers for calculating the evolutionary conservation of amino acid positions in proteins using an empirical Bayesian inference, starting from protein structure and sequence, respectively. Here, we present the new version of the ConSurf web server that combines the two independent servers, providing an easier and more intuitive step-by-step interface, while offering the user more flexibility during the process. In addition, the new version of ConSurf calculates the evolutionary rates for nucleic acid sequences. The new version is freely available at: http://consurf.tau.ac.il/.