This paper reports recent efforts to further improve the performance of the Sphinx system for speaker-independent continuous speech recognition. The recognition error rate is significantly reduced with incorporation of additional dynamic features, semi-continuous hidden Markov models, and speaker clustering. For the June 1990 (RM2) evaluation test set, the error rates of our current system are ...

Current phrase-based statistical machine translation systems process each test sentence in isolation and do not enforce global consistency constraints, even though the test data is often internally consistent with respect to topic or style. We propose a new consistency model for machine translation in the form of a graph-based semi-supervised learning algorithm that exploits similarities betwee...

How to filtering false positives is a fundamental problem of IDS. Constructing alert classification model is one of efficient methods. However, the high cost of preparing training data and classification feature selection are key points in the problem. This paper gives a semi-supervised alert classification model which makes use of the power of semisupervised learning. Moreover, four classifica...

As any other text categorization task, authorship attribution requires a large number of training examples. These examples, which are easily obtained for most of the tasks, are particularly difficult to obtain for this case. Based on this fact, in this paper we investigate the possibility of using Webbased text mining methods for the identification of the author of a given poem. In particular, ...

This paper is concerned with a new task of ranking, referred to as “supplementary data assisted ranking”, or “supplementary ranking” for short. Different from conventional ranking, in the new task, each query is associated with two sets of objects: the target objects that are to be ranked, and the supplementary objects whose orders are not of our interest. Existing learning to rank approaches (...

We investigate the use of Semi-Supervised Learning (SSL) in opinion detection both in sparse data situations and for domain adaptation. We show that co-training reaches the best results in an in-domain setting with small labeled data sets, with a maximum absolute gain of 33.5%. For domain transfer, we show that self-training gains an absolute improvement in labeling accuracy for blog data of 16...

Human action recognition from video sequences is a challenging problem due to the large changes of human appearance in the cases of partial occlusions, non-rigid deformations, and high irregularities. It is difficult to collect a large set of training samples to learn the discriminative model with covering all possible variations of an action. In this paper, we propose an online recognition met...

The graph convolutional networks (GCN) recently proposed by Kipf and Welling are an effective graph model for semi-supervised learning. This model, however, was originally designed to be learned with the presence of both training and test data. Moreover, the recursive neighborhood expansion across layers poses time and memory challenges for training with large, dense graphs. To relax the requir...

This paper proposes a novel image segmentation approach that integrates fully convolutional networks (FCNs) with a level set model. Compared with a FCN, the integrated method can incorporate smoothing and prior information to achieve an accurate segmentation. Furthermore, different than using the level set model as a post-processing tool, we integrate it into the training phase to fine-tune the...

semi-regular locales are extensions of the classical semiregularspaces. we investigate the conditions such that semi-regularizationis a functor. we also investigate the conditions such that semi-regularizationis a reflection or coreflection.