Random Indexing K-tree

Random Indexing K-tree is the combination of two algorithms suited for large scale document clustering.

Interventions for preventing and managing radiation-induced skin reactions in cancer patients (Protocol)

To assess the effects of any interventions which aim to prevent or manage radiation-induced skin reactions in people with cancer.

Clustering with random indexing K-tree and XML structure

This paper describes the approach taken to the clustering task at INEX 2009 by a group at the Queensland University of Technology. The Random Indexing (RI) K-tree has been used with a representation that is based on the semantic markup available in the INEX 2009 Wikipedia collection. The RI K-tree is a scalable approach to clustering large document collections. This approach has produced quality clustering when evaluated using two different methodologies.

Metadata aggregation : a critical component of research infrastructure for the future

The development of research data management infrastructure and services and making research data more discoverable and accessible to the research community is a key priority at the national, state and individual university level. This paper will discuss and reflect upon a collaborative project between Griffith University and the Queensland University of Technology to commission a Metadata Hub or Metadata Aggregation service based upon open source software components. It will describe the role that metadata aggregation services play in modern research infrastructure and argue that this role is a critical one.

Towards improved speech recognition for resource poor languages

In recent times, the improved levels of accuracy obtained by Automatic Speech Recognition (ASR) technology has made it viable for use in a number of commercial products. Unfortunately, these types of applications are limited to only a few of the world’s languages, primarily because ASR development is reliant on the availability of large amounts of language specific resources. This motivates the need for techniques which reduce this language-specific, resource dependency. Ideally, these approaches should generalise across languages, thereby providing scope for rapid creation of ASR capabilities for resource poor languages. Cross Lingual ASR emerges as a means for addressing this need. Underpinning this approach is the observation that sound production is largely influenced by the physiological construction of the vocal tract, and accordingly, is human, and not language specific. As a result, a common inventory of sounds exists across languages; a property which is exploitable, as sounds from a resource poor, target language can be recognised using models trained on resource rich, source languages. One of the initial impediments to the commercial uptake of ASR technology was its fragility in more challenging environments, such as conversational telephone speech. Subsequent improvements in these environments has gained consumer confidence. Pragmatically, if cross lingual techniques are to considered a viable alternative when resources are limited, they need to perform under the same types of conditions. Accordingly, this thesis evaluates cross lingual techniques using two speech environments; clean read speech and conversational telephone speech. Languages used in evaluations are German, Mandarin, Japanese and Spanish. Results highlight that previously proposed approaches provide respectable results for simpler environments such as read speech, but degrade significantly when in the more taxing conversational environment. Two separate approaches for addressing this degradation are proposed. The first is based on deriving better target language lexical representation, in terms of the source language model set. The second, and ultimately more successful approach, focuses on improving the classification accuracy of context-dependent (CD) models, by catering for the adverse influence of languages specific phonotactic properties. Whilst the primary research goal in this thesis is directed towards improving cross lingual techniques, the catalyst for investigating its use was based on expressed interest from several organisations for an Indonesian ASR capability. In Indonesia alone, there are over 200 million speakers of some Malay variant, provides further impetus and commercial justification for speech related research on this language. Unfortunately, at the beginning of the candidature, limited research had been conducted on the Indonesian language in the field of speech science, and virtually no resources existed. This thesis details the investigative and development work dedicated towards obtaining an ASR system with a 10000 word recognition vocabulary for the Indonesian language.

Calculating shades of meaning in semantic spaces

This thesis introduces the problem of conceptual ambiguity, or Shades of Meaning (SoM) that can exist around a term or entity. As an example consider President Ronald Reagan the ex-president of the USA, there are many aspects to him that are captured in text; the Russian missile deal, the Iran-contra deal and others. Simply finding documents with the word “Reagan” in them is going to return results that cover many different shades of meaning related to "Reagan". Instead it may be desirable to retrieve results around a specific shade of meaning of "Reagan", e.g., all documents relating to the Iran-contra scandal. This thesis investigates computational methods for identifying shades of meaning around a word, or concept. This problem is related to word sense ambiguity, but is more subtle and based less on the particular syntactic structures associated with or around an instance of the term and more with the semantic contexts around it. A particularly noteworthy difference from typical word sense disambiguation is that shades of a concept are not known in advance. It is up to the algorithm itself to ascertain these subtleties. It is the key hypothesis of this thesis that reducing the number of dimensions in the representation of concepts is a key part of reducing sparseness and thus also crucial in discovering their SoMwithin a given corpus.

Workflows, processes and technical solutions for seeding the research data commons

Queensland University of Technology (QUT) completed an Australian National Data Service (ANDS) funded “Seeding the Commons Project” to contribute metadata to Research Data Australia. The project employed two Research Data Librarians from October 2009 through to July 2010. Technical support for the project was provided by QUT’s High Performance Computing and Research Support Specialists. ---------- The project identified and described QUT’s category 1 (ARC / NHMRC) research datasets. Metadata for the research datasets was stored in QUT’s Research Data Repository (Architecta Mediaflux). Metadata which was suitable for inclusion in Research Data Australia was made available to the Australian Research Data Commons (ARDC) in RIF-CS format. ---------- Several workflows and processes were developed during the project. 195 data interviews took place in connection with 424 separate research activities which resulted in the identification of 492 datasets. ---------- The project had a high level of technical support from QUT High Performance Computing and Research Support Specialists who developed the Research Data Librarian interface to the data repository that enabled manual entry of interview data and dataset metadata, creation of relationships between repository objects. The Research Data Librarians mapped the QUT metadata repository fields to RIF-CS and an application was created by the HPC and Research Support Specialists to generate RIF-CS files for harvest by the Australian Research Data Commons (ARDC). ---------- This poster will focus on the workflows and processes established for the project including: ---------- • Interview processes and instruments • Data Ingest from existing systems (including mapping to RIF-CS) • Data entry and the Data Librarian interface to Mediaflux • Verification processes • Mapping and creation of RIF-CS for the ARDC

Semantic oscillations : encoding context and structure in complex valued holographic vectors

In computational linguistics, information retrieval and applied cognition, words and concepts are often represented as vectors in high dimensional spaces computed from a corpus of text. These high dimensional spaces are often referred to as Semantic Spaces. We describe a novel and efficient approach to computing these semantic spaces via the use of complex valued vector representations. We report on the practical implementation of the proposed method and some associated experiments. We also briefly discuss how the proposed system relates to previous theoretical work in Information Retrieval and Quantum Mechanics and how the notions of probability, logic and geometry are integrated within a single Hilbert space representation. In this sense the proposed system has more general application and gives rise to a variety of opportunities for future research.