Quantum Mechanics of Semantic Space

Presentation about information modelling and artificial intelligence, semantic structure, cognitive processing and quantum theory.

Generalising unitary time evolution

In this third Quantum Interaction (QI) meeting it is time to examine our failures. One of the weakest elements of QI as a field, arises in its continuing lack of models displaying proper evolutionary dynamics. This paper presents an overview of the modern generalised approach to the derivation of time evolution equations in physics, showing how the notion of symmetry is essential to the extraction of operators in quantum theory. The form that symmetry might take in non-physical models is explored, with a number of viable avenues identified.

Is there something quantum-like about the human mental lexicon?

Following an early claim by Nelson & McEvoy suggesting that word associations can display `spooky action at a distance behaviour', a serious investigation of the potentially quantum nature of such associations is currently underway. In this paper quantum theory is proposed as a framework suitable for modelling the mental lexicon, specifically the results obtained from both intralist and extralist word association experiments. Some initial models exploring this hypothesis are discussed, and they appear to be capable of substantial agreement with pre-existing experimental data. The paper concludes with a discussion of some experiments that will be performed in order to test these models.

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.

The structure and connectivity of semantic memory in the healthy older adult brain

The anterior temporal lobes (ATLs) have been proposed to serve as a "hub" linking amodal or domain general information about the meaning of words, objects, facts and people distributed throughout the brain in semantic memory. The two primary sources of evidence supporting this proposal, viz. structural imaging studies in semantic dementia (SD) patients and functional imaging investigations, are not without problems. Similarly, knowledge about the anatomo-functional connectivity of semantic memory is limited to a handful of intra-operative electrocortical stimulation (IES) investigations in patients. Here, using principal components analyses (PCA) of a battery of conceptual and non-conceptual tests coupled with voxel based morphometry (VBM) and diffusion tensor imaging (DTI) in a sample of healthy older adults aged 55-85. years, we show that amodal semantic memory relies on a predominantly left lateralised network of grey matter regions involving the ATL, posterior temporal and posterior inferior parietal lobes, with prominent involvement of the left inferior fronto-occipital fasciculus (IFOF) and uncinate fasciculus fibre pathways. These results demonstrate relationships between semantic memory, brain structure and connectivity essential for human communication and cognition.

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.

Utilising semantic tags in XML clustering

This paper presents an overview of the experiments conducted using Hybrid Clustering of XML documents using Constraints (HCXC) method for the clustering task in the INEX 2009 XML Mining track. This technique utilises frequent subtrees generated from the structure to extract the content for clustering the XML documents. It also presents the experimental study using several data representations such as the structure-only, content-only and using both the structure and the content of XML documents for the purpose of clustering them. Unlike previous years, this year the XML documents were marked up using the Wiki tags and contains categories derived by using the YAGO ontology. This paper also presents the results of studying the effect of these tags on XML clustering using the HCXC method.

Semantic modeling method for configurable enterprise information systems

Business practices vary from one company to another and business practices often need to be changed due to changes of business environments. To satisfy different business practices, enterprise systems need to be customized. To keep up with ongoing business practice changes, enterprise systems need to be adapted. Because of rigidity and complexity, the customization and adaption of enterprise systems often takes excessive time with potential failures and budget shortfall. Moreover, enterprise systems often drag business behind because they cannot be rapidly adapted to support business practice changes. Extensive literature has addressed this issue by identifying success or failure factors, implementation approaches, and project management strategies. Those efforts were aimed at learning lessons from post implementation experiences to help future projects. This research looks into this issue from a different angle. It attempts to address this issue by delivering a systematic method for developing flexible enterprise systems which can be easily tailored for different business practices or rapidly adapted when business practices change. First, this research examines the role of system models in the context of enterprise system development; and the relationship of system models with software programs in the contexts of computer aided software engineering (CASE), model driven architecture (MDA) and workflow management system (WfMS). Then, by applying the analogical reasoning method, this research initiates a concept of model driven enterprise systems. The novelty of model driven enterprise systems is that it extracts system models from software programs and makes system models able to stay independent of software programs. In the paradigm of model driven enterprise systems, system models act as instructors to guide and control the behavior of software programs. Software programs function by interpreting instructions in system models. This mechanism exposes the opportunity to tailor such a system by changing system models. To make this true, system models should be represented in a language which can be easily understood by human beings and can also be effectively interpreted by computers. In this research, various semantic representations are investigated to support model driven enterprise systems. The significance of this research is 1) the transplantation of the successful structure for flexibility in modern machines and WfMS to enterprise systems; and 2) the advancement of MDA by extending the role of system models from guiding system development to controlling system behaviors. This research contributes to the area relevant to enterprise systems from three perspectives: 1) a new paradigm of enterprise systems, in which enterprise systems consist of two essential elements: system models and software programs. These two elements are loosely coupled and can exist independently; 2) semantic representations, which can effectively represent business entities, entity relationships, business logic and information processing logic in a semantic manner. Semantic representations are the key enabling techniques of model driven enterprise systems; and 3) a brand new role of system models; traditionally the role of system models is to guide developers to write system source code. This research promotes the role of system models to control the behaviors of enterprise.

Reading in the Australian curriculum English : describing the effects of structure and organisation on multimodal texts

The recently introduced Australian Curriculum: English Version 3.0 (Australian Curriculum, Assessment and Reporting Authority [ACARA], 2012) requires students to ‘read’ multimodal text and describe the effects of structure and organisation. We begin this article by tracing the variable understandings of what reading multimodal text might entail through the Framing Paper (National Curriculum Board, 2008), the Framing Paper Consultation Report (National Curriculum Board, 2009a), the Shaping Paper (National Curriculum Board, 2009b) and Version 3.0 of the Australian Curriculum English (ACARA, 2012). Our findings show that the theoretical and descriptive framework for doing so is implicit. Drawing together multiple but internally coherent theories from the field of semiotics, we suggest one way to work towards three Year 5 learning outcomes from the reading/writing mode. The affordances of assembling a broad but explicit technical metalanguage for an informed reading of the integrated design elements of multimodal texts are noted.

Real, complex, and binary semantic vectors

This paper presents a combined structure for using real, complex, and binary valued vectors for semantic representation. The theory, implementation, and application of this structure are all significant. For the theory underlying quantum interaction, it is important to develop a core set of mathematical operators that describe systems of information, just as core mathematical operators in quantum mechanics are used to describe the behavior of physical systems. The system described in this paper enables us to compare more traditional quantum mechanical models (which use complex state vectors), alongside more generalized quantum models that use real and binary vectors. The implementation of such a system presents fundamental computational challenges. For large and sometimes sparse datasets, the demands on time and space are different for real, complex, and binary vectors. To accommodate these demands, the Semantic Vectors package has been carefully adapted and can now switch between different number types comparatively seamlessly. This paper describes the key abstract operations in our semantic vector models, and describes the implementations for real, complex, and binary vectors. We also discuss some of the key questions that arise in the field of quantum interaction and informatics, explaining how the wide availability of modelling options for different number fields will help to investigate some of these questions.

Semantic labelling for document feature patterns using ontological subjects

Finding and labelling semantic features patterns of documents in a large, spatial corpus is a challenging problem. Text documents have characteristics that make semantic labelling difficult; the rapidly increasing volume of online documents makes a bottleneck in finding meaningful textual patterns. Aiming to deal with these issues, we propose an unsupervised documnent labelling approach based on semantic content and feature patterns. A world ontology with extensive topic coverage is exploited to supply controlled, structured subjects for labelling. An algorithm is also introduced to reduce dimensionality based on the study of ontological structure. The proposed approach was promisingly evaluated by compared with typical machine learning methods including SVMs, Rocchio, and kNN.

Some extensions to representation and encoding of structure in models of distributional semantics

This thesis makes several contributions towards improved methods for encoding structure in computational models of word meaning. New methods are proposed and evaluated which address the requirement of being able to easily encode linguistic structural features within a computational representation while retaining the ability to scale to large volumes of textual data. Various methods are implemented and evaluated on a range of evaluation tasks to demonstrate the effectiveness of the proposed methods.

Mapping semantic knowledge for unsupervised text categorisation

Text categorisation is challenging, due to the complex structure with heterogeneous, changing topics in documents. The performance of text categorisation relies on the quality of samples, effectiveness of document features, and the topic coverage of categories, depending on the employing strategies; supervised or unsupervised; single labelled or multi-labelled. Attempting to deal with these reliability issues in text categorisation, we propose an unsupervised multi-labelled text categorisation approach that maps the local knowledge in documents to global knowledge in a world ontology to optimise categorisation result. The conceptual framework of the approach consists of three modules; pattern mining for feature extraction; feature-subject mapping for categorisation; concept generalisation for optimised categorisation. The approach has been promisingly evaluated by compared with typical text categorisation methods, based on the ground truth encoded by human experts.

The implicit structure of positive characteristics

The implicit structure of positive character traits was examined in two studies of 190 and 100 undergraduates. Participants judged the pairwise covariation or semantic similarity of 42 positive characteristics using a sorting or a rating task. Characteristics were drawn from a new classification of strengths and virtues, the Five-Factor Model, and a taxonomy of values. Participants showed consistent patterns of perceived association among the characteristics across the study conditions. Multidimensional scaling yielded three consistent dimensions underlying these judgments (“warmth vs. self-control,” “vivacity vs. decency,” and “wisdom vs. power”). Cluster analyses yielded six consistent groupings—“self-control,” “love,” “wisdom,” “drive,” “vivacity,” and “collaboration”—that corresponded only moderately to the virtue classification. All three taxonomies were systematically related to this implicit structure, but none captured it satisfactorily on its own. Revisions to positive psychology’s classification of strengths are proposed.

Student understandings of numeracy problems: Semantic alignment and analogical reasoning

Despite compulsory mathematics throughout primary and junior secondary schooling, many schools across Australia continue in their struggle to achieve satisfactory numeracy levels. Numeracy is not a distinct subject in school curriculum, and in fact appears as a general capability in the Australian Curriculum, wherein all teachers across all curriculum areas are responsible for numeracy. This general capability approach confuses what numeracy should look like, especially when compared to the structure of numeracy as defined on standardised national tests. In seeking to define numeracy, schools tend to look at past NAPLAN papers, and in doing so, we do not find examples drawn from the various aspects of school curriculum. What we find are more traditional forms of mathematical worded problems.