In this paper, we propose an efficient embedding for modeling higherorder (n-gram) phrases that projects the n-grams to low-dimensional latent semantic space, where a classification function can be defined. We utilize a deep neural network to build a unified discriminative framework that allows for estimating the parameters of the latent space as well as the classification function with a bias for the target classification task at hand. We apply the framework to large-scale sentimental classification task. We present comparative evaluation of the proposed method on two (large) benchmark data sets for online product reviews. The proposed method achieves superior performance in comparison to the state of the art.

No abstract

Our recent work has described a framework for matching solid of mechanical artifacts models based on scale-space feature decomposition. In this work we adopt a method of comparing solid models based on Multiresolutional Reeb Graphs (MRG) similarity computations. This method was originally proposed by Hilaga et al. in [1]. Reeb Graph technique applies MRG structure to comparisons of approximate models found in the graphics community, such as polygonal meshes, faceted representation and Virtual Reality Modeling Language (VRML) models. First, we provide a brief review of shape matching using Multiresolutional Reeb Graphs and present an approach to matching solid models. Second, we show the performance of the Reeb Graph technique when handling primitive CAD models, such as cubes and spheres; then we perform experiments with more complex models, such as LEGO models and mechanical parts, and we discuss Reeb Graph technique’s performance on complex CAD models. Third, we emphasize several problems with the existing technique. Finally, we conclude with discussion of future work.

Abstract. In this paper, we introduce a novel approach for modeling n-grams in a latent space learned from supervised signals. The proposed procedure uses only unigram features to model short phrases (n-grams) in the latent space. The phrases are then combined to form document-level latent representation for a given text, where position of an n-gram in the document is used to compute corresponding combining weight. The resulting two-stage supervised embedding is then coupled with a classifier to form an end-to-end system that we apply to the large-scale sentiment classification task. The proposed model does not require feature selection to retain effective features during pre-processing, and its parameter space grows linearly with size of n-gram. We present comparative evaluations of this method using two large-scale datasets for sentiment classification in online reviews (Amazon and TripAdvisor). The proposed method outperforms standard baselines that rely on bag-of-words representation populated with ngram features.

While benchmark datasets have been proposed for testing computer vision and 3D shape retrieval algorithms, no such datasets have yet been put forward to assess the relevance of these techniques for engineering problems. This paper presents several distinctive benchmark datasets for evaluating techniques for automated classification and retrieval of CAD objects. These datasets include (1) a dataset of CAD primitives (such as those common in constructive solid geometry modeling); (2) two datasets consisting of classes generated by minor topological variation; (3) two datasets of industrial CAD models classified based on object function and manufacturing process, respectively; (4) and a dataset of LEGO c models from the Mindstorms c robotics kits. Each model in the datasets is available in three formats -ACIS SAT, ISO STEP, and as a VRML mesh (some models are available under several different fidelity settings). These are all available through the National Design Repository.Using these datasets, we present comprehensive empirical results for nine (9) different shape and solid model matching and retrieval techniques. These experiments show, as expected, that the quality of precision-recall performance can significantly vary on different datasets. These experiments reveal that for certain object classes and classifications, such as those based on manufacturing processes, all existing techniques perform poorly. This study reveals the strengths and weaknesses of existing research in these areas, introduces open challenge problems, and provides meaningful datasets and metrics against which the success of current and future work can be measured.