Semi-supervised learning of statistical models for natural language understanding

Natural language understanding is to specify a computational model that maps sentences to their semantic mean representation. In this paper, we propose a novel framework to train the statistical models without using expensive fully annotated data. In particular, the input of our framework is a set of sentences labeled with abstract semantic annotations. These annotations encode the underlying embedded semantic structural relations without explicit word/semantic tag alignment. The proposed framework can automatically induce derivation rules that map sentences to their semantic meaning representations. The learning framework is applied on two statistical models, the conditional random fields (CRFs) and the hidden Markov support vector machines (HM-SVMs). Our experimental results on the DARPA communicator data show that both CRFs and HM-SVMs outperform the baseline approach, previously proposed hidden vector state (HVS) model which is also trained on abstract semantic annotations. In addition, the proposed framework shows superior performance than two other baseline approaches, a hybrid framework combining HVS and HM-SVMs and discriminative training of HVS, with a relative error reduction rate of about 25% and 15% being achieved in F-measure.

Undergraduate research training and graduate recruitment

Purpose – Formal opportunities for psychology undergraduates to carry out research training are starting to emerge. In spite of the fact that such training programmes would have a high authentic learning component little is known of undergraduate expectations and attitudes towards such programmes. This paper aims to focus on the issues. Methodology/design/approach – In total, 108 undergraduate participants were surveyed in two experiments that recorded both the prospective and retrospective attitudes towards research training participation. Questionnaires and focus groups were employed and the data were triangulated together to converge on an understanding of student expectations towards authentic learning programmes. Findings – While psychology undergraduates expect to be trained in contemporary research techniques it is the sense of community development that is the prime motivator for participation. Originality/value – The paper places these findings within the context of increasing the employability profile of the undergraduate cohort.

The Principles of Creation of Teaching Materials and Organization of Ukrainian Language Learning Process using Distance Support in Senior Classes

The article deals with the topicality and problems of using information and communication technologies in secondary education, conditions and methods for Ukrainian language learning with the distance support in senior classes. The article shows the principal similarity of distance learning to training one. The common and specific principles of creation of teaching materials for a distance learning course are described. It reveals the conditions of effective organization of Ukrainian language learning with distance support on the material of distance course “Business Ukrainian and Culture of Communication”.

Forming of Learning Set for Neural Networks in Problems of Losless Data Compression

questions of forming of learning sets for artificial neural networks in problems of lossless data compression are considered. Methods of construction and use of learning sets are studied. The way of forming of learning set during training an artificial neural network on the data stream is offered.

Learning higher-level features with convolutional restricted Boltzmann machines for sentiment analysis

In recent years, learning word vector representations has attracted much interest in Natural Language Processing. Word representations or embeddings learned using unsupervised methods help addressing the problem of traditional bag-of-word approaches which fail to capture contextual semantics. In this paper we go beyond the vector representations at the word level and propose a novel framework that learns higher-level feature representations of n-grams, phrases and sentences using a deep neural network built from stacked Convolutional Restricted Boltzmann Machines (CRBMs). These representations have been shown to map syntactically and semantically related n-grams to closeby locations in the hidden feature space. We have experimented to additionally incorporate these higher-level features into supervised classifier training for two sentiment analysis tasks: subjectivity classification and sentiment classification. Our results have demonstrated the success of our proposed framework with 4% improvement in accuracy observed for subjectivity classification and improved the results achieved for sentiment classification over models trained without our higher level features.

EnDNA-Prot:identification of DNA-binding proteins by applying ensemble learning

DNA-binding proteins are crucial for various cellular processes, such as recognition of specific nucleotide, regulation of transcription, and regulation of gene expression. Developing an effective model for identifying DNA-binding proteins is an urgent research problem. Up to now, many methods have been proposed, but most of them focus on only one classifier and cannot make full use of the large number of negative samples to improve predicting performance. This study proposed a predictor called enDNA-Prot for DNA-binding protein identification by employing the ensemble learning technique. Experiential results showed that enDNA-Prot was comparable with DNA-Prot and outperformed DNAbinder and iDNA-Prot with performance improvement in the range of 3.97-9.52% in ACC and 0.08-0.19 in MCC. Furthermore, when the benchmark dataset was expanded with negative samples, the performance of enDNA-Prot outperformed the three existing methods by 2.83-16.63% in terms of ACC and 0.02-0.16 in terms of MCC. It indicated that enDNA-Prot is an effective method for DNA-binding protein identification and expanding training dataset with negative samples can improve its performance. For the convenience of the vast majority of experimental scientists, we developed a user-friendly web-server for enDNA-Prot which is freely accessible to the public. © 2014 Ruifeng Xu et al.

TQM in e-Learning: a Self-assessment Model and Questionnaire

Organizations are seeking new, integrated systems that enable rapid changes through early identification of opportunities and problems, tracking of progress against plans, flexible allocation of resources to achieve goals, and consistent operations. Total Quality Management (TQM) is an overall business strategy. It means that all activities of the company will be focused on satisfying all stakeholders of the company. TQM can be realised by using the EFQM model. The EFQM model is a tool that organizations may use as a framework for self-evaluation that enables an organization to identify its strengths and areas for improvement and the extent to which its operations and results are in line with the characteristics of an excellent organization. We focus on a training organisation or to the learning department of an organization. So we are limiting the EFQM model to the training /learning activities. We can apply EFQM perfect on the level of an activity (business line) of a company. We selected the main criteria for which the learner can play the role of assessor. So only three main criteria left: the enabling resources, the enabling processes and the (learning) results for the learner. We limited the last one to “learning results” based on the Kirkpatrick model.

The Conception of Creation of Integrated Development Environment for Computer Training Systems

The various questions of creation of integrated development environment for computer training systems are considered in the given paper. The information technologies that can be used for creation of the integrated development environment are described. The different didactic aspects of realization of such systems are analyzed. The ways to improve the efficiency and quality of learning process with computer training systems for distance education are pointed.

e-Learning, e-Practising and e-Tutoring: an Integrated Approach

In this paper is described a didactic methodology combining current e-learning methods and the support of Intelligent Agents technologies. The aim is to favor the synthesis among theoretical approach and based practical approach using the so-called Intelligent Agent, software that exploits the Artificial Intelligence and that operates as tutor, facilitating the consumers in the training operations. The paper illustrates how such new Intelligent Agent algorithm (IA) is used in the training of employees working in the transportation sector, thanks to the experience gained with the PARMENIDE project - Promoting Advanced Resources and Methodologies for New Teaching and Learning Solutions in Digital Education.