A large ontology such as lexical ontology is useful as the basic knowledge base in artificial intelligence and computational linguistics application. However, it is insufficient to recognize only existing instances for each concept. Adding new instances into the lexical ontology will expand knowledge in the system. In this paper, we propose an efficient unsupervised ontology population system t...

Domains such as text, images etc contain large amounts of redundancies and ambiguities among the attributes which result in considerable noise effects (i.e. the data is high dimension). Retrieving the data from high dimensional datasets is a big challenge. Dimensionality reduction techniques have been a successful avenue for automatically extracting the latent concepts by removing the noise and...

In [3] it was demonstrated for the first time that crossing minimization of bipartite graphs can be used to perform unsupervised clustering. In this paper, we will present the detailed analysis of the bipartite graph model used to perform unsupervised clustering as in [1, 2, 3]. We will also discuss the effect of data discretization, followed by simulation results demonstrating the noise immuni...

In this paper, a new unsupervised learning algorithm, namely Nonnegative Discriminative Feature Selection (NDFS), is proposed. To exploit the discriminative information in unsupervised scenarios, we perform spectral clustering to learn the cluster labels of the input samples, during which the feature selection is performed simultaneously. The joint learning of the cluster labels and feature sel...

The predominant strategy for facial expressions analysis and temporal analysis of facial events is the following: a generic facial landmarks tracker, usually trained on thousands of carefully annotated examples, is applied to track the landmark points, and then analysis is performed using mostly the shape andmore rarely the facial texture. This paper challenges the above framework by showing th...

This paper presents two unsupervised learning layers (UL layers) for label-free video analysis: one for fully connected layers, and the other for convolutional ones. The proposed UL layers can play two roles: they can be the cost function layer for providing global training signal; meanwhile they can be added to any regular neural network layers for providing local training signals and combined...

We present a novel unsupervised approach for multilingual sentiment analysis driven by compositional syntax-based rules. On the one hand, we exploit some of the main advantages of unsupervised algorithms: (1) the interpretability of their output, in contrast with most supervised models, which behave as a black box and (2) their robustness across different corpora and domains. On the other hand,...

Conventional speaker-independent HMMs ignore the speaker di erences and collect speech data in an observation space. This causes a problem that the output probability distribution of the HMMs becomes vague so that it deteriorates the recognition accuracy. To solve this problem, we construct the speaker subspace for an individual speaker and correlate them by o-space canonical correlation analys...

Feature selection is an important technique in machine learning research. An effective and robust feature selection method is desired to simultaneously identify the informative features and eliminate the noisy ones of data. In this paper, we consider the unsupervised feature selection problem which is particularly difficult as there is not any class labels that would guide the search for releva...