Learning task specific distributed paragraph representations using a 2-tier convolutional neural network

We introduce a type of 2-tier convolutional neural network model for learning distributed paragraph representations for a special task (e.g. paragraph or short document level sentiment analysis and text topic categorization). We decompose the paragraph semantics into 3 cascaded constitutes: word representation, sentence composition and document composition. Specifically, we learn distributed word representations by a continuous bag-of-words model from a large unstructured text corpus. Then, using these word representations as pre-trained vectors, distributed task specific sentence representations are learned from a sentence level corpus with task-specific labels by the first tier of our model. Using these sentence representations as distributed paragraph representation vectors, distributed paragraph representations are learned from a paragraph-level corpus by the second tier of our model. It is evaluated on DBpedia ontology classification dataset and Amazon review dataset. Empirical results show the effectiveness of our proposed learning model for generating distributed paragraph representations.

Dynamic iterative ontology learning

The fundamental failure of current approaches to ontology learning is to view it as single pipeline with one or more specific inputs and a single static output. In this paper, we present a novel approach to ontology learning which takes an iterative view of knowledge acquisition for ontologies. Our approach is founded on three open-ended resources: a set of texts, a set of learning patterns and a set of ontological triples, and the system seeks to maintain these in equilibrium. As events occur which disturb this equilibrium, actions are triggered to re-establish a balance between the resources. We present a gold standard based evaluation of the final output of the system, the intermediate output showing the iterative process and a comparison of performance using different seed input. The results are comparable to existing performance in the literature.

Ontologies, taxonomies, thesauri:learning from texts

The use of ontologies as representations of knowledge is widespread but their construction, until recently, has been entirely manual. We argue in this paper for the use of text corpora and automated natural language processing methods for the construction of ontologies. We delineate the challenges and present criteria for the selection of appropriate methods. We distinguish three ma jor steps in ontology building: associating terms, constructing hierarchies and labelling relations. A number of methods are presented for these purposes but we conclude that the issue of data-sparsity still is a ma jor challenge. We argue for the use of resources external tot he domain specific corpus.

The impact of learning outcomes in business education: assessing value, relevance and graduate ability in a multi-country study of employers and business graduates

This paper discusses critical findings from a two-year EU-funded research project involving four European countries: Austria, England, Slovenia and Romania. The project had two primary aims. The first of these was to develop a systematic procedure for assessing the balance between learning outcomes acquired in education and the specific needs of the labour market. The second aim was to develop and test a set of meta-level quality indicators aimed at evaluating the linkages between education and employment. The project was distinctive in that it combined different partners from Higher Education, Vocational Training, Industry and Quality Assurance. One of the key emergent themes identified in exploratory interviews was that employers and recent business graduates in all four countries want a well-rounded education which delivers a broad foundation of key business knowledge across the various disciplines. Both groups also identified the need for personal development in critical skills and competencies. Following the exploratory study, a questionnaire was designed to address five functional business areas, as well as a cluster of 8 business competencies. Within the survey, questions relating to the meta-level quality indicators assessed the impact of these learning outcomes on the workplace, in terms of the following: 1) value, 2) relevance and 3) graduate ability. This paper provides an overview of the study findings from a sample of 900 business graduates and employers. Two theoretical models are proposed as tools for predicting satisfaction with work performance and satisfaction with business education. The implications of the study findings for education, employment and European public policy are discussed.

Finite-size effects in on-line learning of multilayer neural networks

We complement recent advances in thermodynamic limit analyses of mean on-line gradient descent learning dynamics in multi-layer networks by calculating fluctuations possessed by finite dimensional systems. Fluctuations from the mean dynamics are largest at the onset of specialisation as student hidden unit weight vectors begin to imitate specific teacher vectors, increasing with the degree of symmetry of the initial conditions. In light of this, we include a term to stimulate asymmetry in the learning process, which typically also leads to a significant decrease in training time.

Category learning induces position invariance of pattern recognition across the visual field

Human object recognition is considered to be largely invariant to translation across the visual field. However, the origin of this invariance to positional changes has remained elusive, since numerous studies found that the ability to discriminate between visual patterns develops in a largely location-specific manner, with only a limited transfer to novel visual field positions. In order to reconcile these contradicting observations, we traced the acquisition of categories of unfamiliar grey-level patterns within an interleaved learning and testing paradigm that involved either the same or different retinal locations. Our results show that position invariance is an emergent property of category learning. Pattern categories acquired over several hours at a fixed location in either the peripheral or central visual field gradually become accessible at new locations without any position-specific feedback. Furthermore, categories of novel patterns presented in the left hemifield are distinctly faster learnt and better generalized to other locations than those learnt in the right hemifield. Our results suggest that during learning initially position-specific representations of categories based on spatial pattern structure become encoded in a relational, position-invariant format. Such representational shifts may provide a generic mechanism to achieve perceptual invariance in object recognition.

Engaging tutors in using e-repositories for learning and teaching

Universities which set up online repositories for the management of learning and teaching resources commonly find that uptake is poor. Tutors are often reluctant to upload their materials to e-repositories, even though the same tutors are happy to upload resources to the virtual learning environment (e.g. Blackboard, Moodle, Sakai) and happy to upload their research papers to the university’s research publications repository. The paper reviews this phenomenon and suggests constructive ways in which tutors can be encouraged to engage with an e-repository. The authors have recently completed a major project “Developing Repositories at Worcester” which is part of a group of similar projects in the UK. The paper includes the feedback and the lessons learned from these projects, based on the publications and reports they have produced. They cover ways of embedding repository use into institutional working practice, and give examples of different types of repository designed to meet the needs of those using different kinds of learning and teaching resources. As well as this specific experience, the authors summarise some of the main findings from UK publications, in particular the December 2008 report of Joint Information Systems Committee: Good intentions: improving the evidence base in support of sharing learning materials and Online Innovation in Higher Education, Ron Cooke’s report to a UK government initiative on the future of Higher Education. The issues covered include the development of Web 2.0 style repositories rather than conventionally structured ones, the use of tags rather than metadata, the open resources initiative, the best use for conventional repositories, links to virtual learning environments, and the processes for the management and support of repositories within universities. In summary the paper presents an optimistic, constructive view of how to embed the use of e-repositories into the working practices of university tutors. Equally, the authors are aware of the considerable difficulties in making progress and are realistic about what can be achieved. The paper uses evidence and experience drawn from those working in this field to suggest a strategic vision in which the management of e-learning resources is productive, efficient and meets the needs of both tutors and their students.

Bridging the gap from the general to the specific by linking knowledge management to business process

A phenomenon common to almost all fields is that there is a gap between theory and practical implementation. However, this is a particular problem in knowledge management, where much of the literature consists of general principles written in the context of a ‘knowledge world’ that has few, if any, references to how to carry out knowledge management in organisations. In this chapter, we put forward the view that the best way to bridge this gap between general principles and the specific issues facing a given organisation is to link knowledge management to the organisation’s business processes. After briefly reviewing, and rejecting alternative ways in which this gap might be bridged, the chapter goes on to explain the justification for, and the potential benefits and snags of, linking knowledge management to business processes. Successful and unsuccessful examples are presented. We concentrate especially on the issues of establishing what knowledge is relevant to an organisation at present, the need for organisational learning to cope with the inevitable change, and the additional problems posed by the growing internationalisation of operations. We conclude that linking knowledge management in terms of business processes is the best route for organisations to follow, but that it is not the answer to all knowledge management problems, especially where different cultures and/or cultural change are involved.

Organisational learning - a critical systems thinking discipline

Original Paper European Journal of Information Systems (2001) 10, 135–146; doi:10.1057/palgrave.ejis.3000394 Organisational learning—a critical systems thinking discipline P Panagiotidis1,3 and J S Edwards2,4 1Deloitte and Touche, Athens, Greece 2Aston Business School, Aston University, Aston Triangle, Birmingham, B4 7ET, UK Correspondence: Dr J S Edwards, Aston Business School, Aston University, Aston Triangle, Birmingham, B4 7ET, UK. E-mail: j.s.edwards@aston.ac.uk 3Petros Panagiotidis is Manager responsible for the Process and Systems Integrity Services of Deloitte and Touche in Athens, Greece. He has a BSc in Business Administration and an MSc in Management Information Systems from Western International University, Phoenix, Arizona, USA; an MSc in Business Systems Analysis and Design from City University, London, UK; and a PhD degree from Aston University, Birmingham, UK. His doctorate was in Business Systems Analysis and Design. His principal interests now are in the ERP/DSS field, where he serves as project leader and project risk managment leader in the implementation of SAP and JD Edwards/Cognos in various major clients in the telecommunications and manufacturing sectors. In addition, he is responsible for the development and application of knowledge management systems and activity-based costing systems. 4John S Edwards is Senior Lecturer in Operational Research and Systems at Aston Business School, Birmingham, UK. He holds MA and PhD degrees (in mathematics and operational research respectively) from Cambridge University. His principal research interests are in knowledge management and decision support, especially methods and processes for system development. He has written more than 30 research papers on these topics, and two books, Building Knowledge-based Systems and Decision Making with Computers, both published by Pitman. Current research work includes the effect of scale of operations on knowledge management, interfacing expert systems with simulation models, process modelling in law and legal services, and a study of the use of artifical intelligence techniques in management accounting. Top of pageAbstract This paper deals with the application of critical systems thinking in the domain of organisational learning and knowledge management. Its viewpoint is that deep organisational learning only takes place when the business systems' stakeholders reflect on their actions and thus inquire about their purpose(s) in relation to the business system and the other stakeholders they perceive to exist. This is done by reflecting both on the sources of motivation and/or deception that are contained in their purpose, and also on the sources of collective motivation and/or deception that are contained in the business system's purpose. The development of an organisational information system that captures, manages and institutionalises meaningful information—a knowledge management system—cannot be separated from organisational learning practices, since it should be the result of these very practices. Although Senge's five disciplines provide a useful starting-point in looking at organisational learning, we argue for a critical systems approach, instead of an uncritical Systems Dynamics one that concentrates only on the organisational learning practices. We proceed to outline a methodology called Business Systems Purpose Analysis (BSPA) that offers a participatory structure for team and organisational learning, upon which the stakeholders can take legitimate action that is based on the force of the better argument. In addition, the organisational learning process in BSPA leads to the development of an intrinsically motivated information organisational system that allows for the institutionalisation of the learning process itself in the form of an organisational knowledge management system. This could be a specific application, or something as wide-ranging as an Enterprise Resource Planning (ERP) implementation. Examples of the use of BSPA in two ERP implementations are presented.

Measuring the influence of similarity on category-specific effects

There is evidence for both advantages and disadvantages in normal recognition of living over nonliving things. This paradox has been attributed to high levels of perceptual similarity within living categories having a different effect on performance in different contexts. However, since living things are intrinsically more similar to each other, previous studies could not determine whether the various category effects were due to perceptual similarity, or to other characteristics of living things. We used novel animal and vehicle stimuli that were matched for similarity to measure the influence of perceptual similarity in different contexts. We found that displaying highly similar objects in blocked sets reduced their perceived similarity, eliminating the detrimental effect on naming performance. Experiment 1 demonstrated a disadvantage for highly similar objects in name learning and name verification using mixed groups of similar and dissimilar animals and vehicles. Experiment 2 demonstrated no disadvantage for the same highly similar objects when they were blocked, e.g., similar animals presented alone. Thus, perceptual similarity, rather than other characteristics particular to living things, is affected by context, and could create apparent category effects under certain testing conditions.

Differential impact of posterior lesions in the left and right hemisphere on visual category learning and generalization to contrast reversal

Hemispheric differences in the learning and generalization of pattern categories were explored in two experiments involving sixteen patients with unilateral posterior, cerebral lesions in the left (LH) or right (RH) hemisphere. In each experiment participants were first trained to criterion in a supervised learning paradigm to categorize a set of patterns that either consisted of simple geometric forms (Experiment 1) or unfamiliar grey-level images (Experiment 2). They were then tested for their ability to generalize acquired categorical knowledge to contrast-reversed versions of the learning patterns. The results showed that RH lesions impeded category learning of unfamiliar grey-level images more severely than LH lesions, whereas this relationship appeared reversed for categories defined by simple geometric forms. With regard to generalization to contrast reversal, categorization performance of LH and RH patients was unaffected in the case of simple geometric forms. However, generalization to of contrast-reversed grey-level images distinctly deteriorated for patients with LH lesions relative to those with RH lesions, with the latter (but not the former) being consistently unable to identify the pattern manipulation. These findings suggest a differential use of contrast information in the representation of pattern categories in the two hemispheres. Such specialization appears in line with previous distinctions between a predominantly lefthemispheric, abstract-analytical and a righthemispheric, specific-holistic representation of object categories, and their prediction of a mandatory representation of contrast polarity in the RH. Some implications for the well-established dissociation of visual disorders for the recognition of faces and letters are discussed.

A psychological investigation into the relationship between hemispheric functioning and specific written language difficulties (dyslexia), using pharmaceutical intervention techniques

This thesis attempts a psychological investigation of hemispheric functioning in developmental dyslexia. Previous work using neuropsychological methods with developmental dyslexics is reviewed ,and original work is presented both of a conventional psychometric nature and also utilising a new means of intervention. At the inception of inquiry into dyslexia, comparisons were drawn between developmental dyslexia and acquired alexia, promoting a model of brain damage as the common cause. Subsequent investigators found developmental dyslexics to be neurologically intact, and so an alternative hypothesis was offered, namely that language is abnormally localized (not in the left hemisphere). Research in the last decade, using the advanced techniques of modern neuropsychology, has indicated that developmental dyslexics are probably left hemisphere dominant for language. The development of a new type of pharmaceutical prep~ration (that appears to have a left hemisphere effect) offers an oppertunity to test the experimental hypothesis. This hypothesis propounds that most dyslexics are left hemisphere language dominant, but some of these language related operations are dysfunctioning. The methods utilised are those of psychological assessment of cognitive function, both in a traditional psychometric situation, and with a new form of intervention (Piracetam). The information resulting from intervention will be judged on its therapeutic validity and contribution to the understanding of hemispheric functioning in dyslexics. The experimental studies using conventional psychometric evaluation revealed a dyslexic profile of poor sequencing and name coding ability, with adequate spatial and verbal reasoning skills. Neuropsychological information would tend to suggest that this profile was indicative of adequate right hemsiphere abilities and deficits in some left hemsiphere abilities. When an intervention agent (Piracetam) was used with young adult dyslexics there were improvements in both the rate of acquisition and conservation of verbal learning. An experimental study with dyslexic children revealed that Piracetam appeared to improve reading, writing and sequencing, but did not influence spatial abilities. This would seem to concord with other recent findings, that deve~mental dyslexics may have left hemisphere language localisation, although some of these language related abilities are dysfunctioning.

Parallel strategy for optimal learning in perceptrons

We developed a parallel strategy for learning optimally specific realizable rules by perceptrons, in an online learning scenario. Our result is a generalization of the Caticha–Kinouchi (CK) algorithm developed for learning a perceptron with a synaptic vector drawn from a uniform distribution over the N-dimensional sphere, so called the typical case. Our method outperforms the CK algorithm in almost all possible situations, failing only in a denumerable set of cases. The algorithm is optimal in the sense that it saturates Bayesian bounds when it succeeds.

Content-based VLE designs improve learning efficiency in constructivist statistics education

Background: We introduced a series of computer-supported workshops in our undergraduate statistics courses, in the hope that it would help students to gain a deeper understanding of statistical concepts. This raised questions about the appropriate design of the Virtual Learning Environment (VLE) in which such an approach had to be implemented. Therefore, we investigated two competing software design models for VLEs. In the first system, all learning features were a function of the classical VLE. The second system was designed from the perspective that learning features should be a function of the course's core content (statistical analyses), which required us to develop a specific-purpose Statistical Learning Environment (SLE) based on Reproducible Computing and newly developed Peer Review (PR) technology. Objectives: The main research question is whether the second VLE design improved learning efficiency as compared to the standard type of VLE design that is commonly used in education. As a secondary objective we provide empirical evidence about the usefulness of PR as a constructivist learning activity which supports non-rote learning. Finally, this paper illustrates that it is possible to introduce a constructivist learning approach in large student populations, based on adequately designed educational technology, without subsuming educational content to technological convenience. Methods: Both VLE systems were tested within a two-year quasi-experiment based on a Reliable Nonequivalent Group Design. This approach allowed us to draw valid conclusions about the treatment effect of the changed VLE design, even though the systems were implemented in successive years. The methodological aspects about the experiment's internal validity are explained extensively. Results: The effect of the design change is shown to have substantially increased the efficiency of constructivist, computer-assisted learning activities for all cohorts of the student population under investigation. The findings demonstrate that a content-based design outperforms the traditional VLE-based design. © 2011 Wessa et al.

Learning sentiment classification model from labeled features

We propose a novel framework where an initial classifier is learned by incorporating prior information extracted from an existing sentiment lexicon. Preferences on expectations of sentiment labels of those lexicon words are expressed using generalized expectation criteria. Documents classified with high confidence are then used as pseudo-labeled examples for automatical domain-specific feature acquisition. The word-class distributions of such self-learned features are estimated from the pseudo-labeled examples and are used to train another classifier by constraining the model's predictions on unlabeled instances. Experiments on both the movie review data and the multi-domain sentiment dataset show that our approach attains comparable or better performance than exiting weakly-supervised sentiment classification methods despite using no labeled documents.