The Constituent-Context Model (CCM) achieves promising results for unsupervised grammar induction. However, its performance drops for longer sentences. In this paper, we describe a general feature-based model for CCM, in which linguistic knowledge can be easily integrated as features. Features take the log-linear form with local normalization, so the Expectation-Maximization (EM) algorithm is s...

This paper addresses the problem of classifying observations when features are context-sensitive, especially when the testing set involves a context that is different from the training set. The paper begins with a precise definition of the problem, then general strategies are presented for enhancing the performance of classification algorithms on this type of problem. These strategies are teste...

For more than two decades, research in the development of context-aware applications has gained significant attention, in which the context aware should be taken into account to adapt them to the requirements of the environment and users. However, advances in application models to support the development of these systems have not kept up. Researchers have been building and deploying context-awa...

Local image features are often used to efficiently represent image content. The limited number of types of features that a local feature extractor responds to might be insufficient to provide a robust image representation. To overcome this limitation, we propose a context-aware feature extraction formulated under an information theoretic framework. The algorithm does not respond to a specific t...

Context based image retrieval is useful to effectively retrieve images based on its context from the massive collection available on the web. Content based image retrieval system is effective only to recognize and retrieve specific objects. It fails when the image has multiple objects and the objects are cluttered. In this work an algorithm has been proposed which facilitates the search based o...

When people categorize an object, they often encode a certain number of its properties for later classification. In Schyns and Murphy (1993), we suggested that the way people group objects into categories could induce the learning of new dimensions of ca egorization--i.e., dimensions that did not exist prior to the experience with the categorization system. In this research, we examine whether ...

We investigate different types of features for language modeling in Arabic automatic speech recognition. While much effort in language modeling research has been directed at designing better models or smoothing techniques for n-gram language models, in this paper we take the approach of augmenting the context in the n-gram model with different sources of information. We start by adding word cla...

Recently, interpretable vector spaces have been introduced, vector spaces in which individual dimensions are meaningful. For polysemous words, interpretable vectors mix features from different senses. In this paper, we propose the task of computing contextspecific interpretable representations for individual senses of a word. Focusing on computing features that describe circumstances of an even...

Convolutional Neural Networks (CNNs) have been shown their performance in speech recognition systems for extracting features, and also acoustic modeling. In addition, CNNs have been used for robust speech recognition and competitive results have been reported. Convolutive Bottleneck Network (CBN) is a kind of CNNs which has a bottleneck layer among its fully connected layers. The bottleneck fea...