Evaluation of unsupervised semantic mapping of natural language with Leximancer concept mapping

The Leximancer system is a relatively new method for transforming lexical co-occurrence information from natural language into semantic patterns in an unsupervised manner. It employs two stages of co-occurrence information extraction-semantic and relational-using a different algorithm for each stage. The algorithms used are statistical, but they employ nonlinear dynamics and machine learning. This article is an attempt to validate the output of Leximancer, using a set of evaluation criteria taken from content analysis that are appropriate for knowledge discovery tasks.

Toxinology in Australia's colonial era: A chronology and perspective of human envenomation in 19th century Australia

The medical management of those envenomed by snakes, spiders and poisonous fish in Australia featured extensively in the writings 19th century doctors, expeditioners and anthropologists. Against the background of this introduced medical doctrine there already existed an extensive tradition of Aboriginal medical lore; techniques of heat treatment, suction, incision and the application of plant-derived pharmacological substances featured extensively in the management of envenomed victims. The application of a hair-string or grass-string ligature, suctioning of the bite-site and incision were practised in a variety of combinations. Such evolved independently of and pre-dated such practices, which were promoted extensively by immigrant European doctors in the late 19th century. Pacific scientific toxinology began in the 17th century with Don Diego de Prado y Tovar's 1606 account of ciguatera. By the end of the 19th century more than 30 papers and books had defined the natural history of Australian elapid poisoning. The medical management of snakebite in Australia was the focus of great controversy from 1860 to 1900. Dogmatic claims of the supposed antidote efficacy of intravenous ammonia by Professor G.B. Halford, and that of strychnine by Dr. Augustus Mueller, claimed mainstream medical attention. This era of potential iatrogenic disaster and dogma was brought to a conclusion by the objective experiments of Joseph Lauterer and Thomas Lane Bancroft in 1890 in Brisbane; and by those of C.J. Martin (from 1893) and Frank Tidswell (from 1898), both of Sydney. The modern era of Australian toxinology developed as a direct consequence of Calmette's discovery, in Paris in 1894, of immune serum, which was protective against snakebite. We review the key contributors and discoveries of toxinology in colonial Australia.

Knowledge management and tourism

The study and practice of knowledge management has grown rapidly since the 90s, driven by social, economic, and technological trends. Tourism has been slow in adopting this app oach due to not only a lack of gearing between researchers and tourism, but also to a 'hostile' knowledge adoption environment. Its acquisition would close the gap and also provide both insights and potential applications for tourism. Research in Australia supports the assertion that this field is a late adopter of knowledge management. In response, this paper provides a model for tourism. (c) 2005 Elsevier Ltd. All rights reserved.

Employment services in an age of e-government

The increasing use of information and communications technologies among government departments and non-government agencies has fundamentally changed the implementation of employment services policy in Australia. The administrative arrangements for governing unemployment and unemployed people are now constituted by a complex contractual interplay between government departments as ‘purchasers’ and a range of small and large private organizations as ‘providers’. Assessing, tracking and monitoring the activities of unemployed people through the various parts of the employment services system has been made possible by developments in information technology and tailored computer programs. Consequently, the discretionary capacity that is traditionally associated with ‘street-level bureaucracy’ has been partly transformed into more prescriptive forms of ‘screen-level bureaucracy’. The knowledge embedded in these new computer-based technologies is considered superior because it is based on ‘objective calculations’, rather than subjective assessments of individual employees. The relationship between the sociopolitical context of unemployment policy and emerging forms of e-government is explored using illustrative findings from a qualitative pilot study undertaken in two Australian sites. The findings suggest that some of the new technologies in the employment services system are welcomed, while other applications are experienced as contradictory to the aims of delivering a personalized and respectful service.

The graying of R&D workgroups: The effects of age diversity on developing publicly usable knowledge

Does the graying of scientific research teams matter? This study addresses how workgroup processes and external environmental factors contribute and inhibit the effect of age diversity in R&D project groups on the production of innovative publicly usable knowledge outcomes in the form of publication outputs. We examined the relationships between group age diversity (age cohort diversity, mean age, age dispersion), R&D workgroup member self-ratings of workgroup processes, their supervisor�s assessment of the external environmental factors the project groups faced, and their supervisor�s ratings of group performance, the number of scientific publicly available publications produced by the group and the use of multiple authorships on publications. Usable data was obtained from 32 R&D workgroups of a large Government Agricultural Research and Development Agency. Consistent with the literature, workgroup processes and external environmental factors were found to directly effect innovation outcomes. Contrary to expectation, but consistent with Social Identity theory, workgroup age diversity generally negatively impacted upon innovation outcomes. An exception was where multiple authorship on publications for project groups increased as the dispersion of age within groups increased. Importantly, workgroups that were both more age homogeneous and perceived to have optimally functioning work processes produced more R&D innovation outcomes than other groups. Generally, these differences appear to be related to the greater division of labor practices (and less multi-tasking) employed by the older and more homogeneous workgroups. Implications for R&D workgroup resource theory and practices are discussed.

Machine learning for matching astronomy catalogues

An emerging issue in the field of astronomy is the integration, management and utilization of databases from around the world to facilitate scientific discovery. In this paper, we investigate application of the machine learning techniques of support vector machines and neural networks to the problem of amalgamating catalogues of galaxies as objects from two disparate data sources: radio and optical. Formulating this as a classification problem presents several challenges, including dealing with a highly unbalanced data set. Unlike the conventional approach to the problem (which is based on a likelihood ratio) machine learning does not require density estimation and is shown here to provide a significant improvement in performance. We also report some experiments that explore the importance of the radio and optical data features for the matching problem.

A border-based approach for hiding sensitive frequent itemsets

Sharing data among organizations often leads to mutual benefit. Recent technology in data mining has enabled efficient extraction of knowledge from large databases. This, however, increases risks of disclosing the sensitive knowledge when the database is released to other parties. To address this privacy issue, one may sanitize the original database so that the sensitive knowledge is hidden. The challenge is to minimize the side effect on the quality of the sanitized database so that nonsensitive knowledge can still be mined. In this paper, we study such a problem in the context of hiding sensitive frequent itemsets by judiciously modifying the transactions in the database. To preserve the non-sensitive frequent itemsets, we propose a border-based approach to efficiently evaluate the impact of any modification to the database during the hiding process. The quality of database can be well maintained by greedily selecting the modifications with minimal side effect. Experiments results are also reported to show the effectiveness of the proposed approach. © 2005 IEEE

Performing traditional knowledge using a game engine: Communicating and sharing Australian Aboriginal knowledge practices

This paper challenges current practices in the use of digital media to communicate Australian Aboriginal knowledge practices in a learning context. It proposes that any digital representation of Aboriginal knowledge practices needs to examine the epistemology and ontology of these practices in order to design digital environments that effectively support and enable existing Aboriginal knowledge practices in the real world. Central to this is the essential task of any new digital representation of Aboriginal knowledge to resolve the conflict between database and narrative views of knowledge (L. Manovich, 2001). This is in order to provide a tool that complements rather than supplants direct experience of traditional knowledge practices (V. Hart, 2001). This paper concludes by reporting on the recent development of an advanced learning technology that addresses this.

Knowledge maintenance and the frame problem

Knowledge maintenance is a major challenge for both knowledge management and the Semantic Web. Operating over the Semantic Web, there will be a network of collaborating agents, each with their own ontologies or knowledge bases. Change in the knowledge state of one agent may need to be propagated across a number of agents and their associated ontologies. The challenge is to decide how to propagate a change of knowledge state. The effects of a change in knowledge state cannot be known in advance, and so an agent cannot know who should be informed unless it adopts a simple ‘tell everyone – everything’ strategy. This situation is highly reminiscent of the classic Frame Problem in AI. We argue that for agent-based technologies to succeed, far greater attention must be given to creating an appropriate model for knowledge update. In a closed system, simple strategies are possible (e.g. ‘sleeping dog’ or ‘cheap test’ or even complete checking). However, in an open system where cause and effect are unpredictable, a coherent cost-benefit based model of agent interaction is essential. Otherwise, the effectiveness of every act of knowledge update/maintenance is brought into question.

Techniques for automated taxonomy building: towards ontologies for knowledge management

Ontologies have become widely accepted as the main method for representing knowledge in Knowledge Management (KM) applica-tions. Given the continuous and rapid change and dynamic nature of knowledge in all fields, automated methods for construct-ing ontologies are of great importance. All ontologies or taxonomies currently in use have been hand built and require consider-able manpower to keep up to date. Taxono-mies are less logically rigorous than ontolo-gies, and in this paper we consider the re-quirements for a system which automatically constructed taxonomies. There are a number of potentially useful methods for construct-ing hierarchically organised concepts from a collection of texts and there are a number of automatic methods which permit one to as-sociate one word with another. The impor-tant issue for the successful development of this research area is to identify techniques for labelling the relation between two candi-date terms, if one exists. We consider a number of possible approaches and argue that the majority are unsuitable for our re-quirements.

User-centred ontology learning for knowledge management

Automatic ontology building is a vital issue in many fields where they are currently built manually. This paper presents a user-centred methodology for ontology construction based on the use of Machine Learning and Natural Language Processing. In our approach, the user selects a corpus of texts and sketches a preliminary ontology (or selects an existing one) for a domain with a preliminary vocabulary associated to the elements in the ontology (lexicalisations). Examples of sentences involving such lexicalisation (e.g. ISA relation) in the corpus are automatically retrieved by the system. Retrieved examples are validated by the user and used by an adaptive Information Extraction system to generate patterns that discover other lexicalisations of the same objects in the ontology, possibly identifying new concepts or relations. New instances are added to the existing ontology or used to tune it. This process is repeated until a satisfactory ontology is obtained. The methodology largely automates the ontology construction process and the output is an ontology with an associated trained leaner to be used for further ontology modifications.

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.

Managing software engineers and their knowledge

This chapter begins by reviewing the history of software engineering as a profession, especially the so-called software crisis and responses to it, to help focus on what it is that software engineers do. This leads into a discussion of the areas in software engineering that are problematic as a basis for considering knowledge management issues. Some of the previous work on knowledge management in software engineering is then examined, much of it not actually going under a knowledge management title, but rather “learning” or “expertise”. The chapter goes on to consider the potential for knowledge management in software engineering and the different types of knowledge management solutions and strategies that might be adopted, and it touches on the crucial importance of cultural issues. It concludes with a list of challenges that knowledge management in software engineering needs to address.

Group perceptions of knowledge management

This paper reports preliminary results of a project investigating how staff in UK organisations perceive knowledge management in their organisation as a group. The group setting appears to be effective in surfacing opinions and enabling progress in both understanding and action to be made. Among the findings thus far are the importance of the knowledge champion role and the state of the “knowledge management life cycle” in each organisation, and continuing confusion between knowledge, information and mechanisms.