A tensor encoding model for semantic processing

This paper develops and evaluates an enhanced corpus based approach for semantic processing. Corpus based models that build representations of words directly from text do not require pre-existing linguistic knowledge, and have demonstrated psychologically relevant performance on a number of cognitive tasks. However, they have been criticised in the past for not incorporating sufficient structural information. Using ideas underpinning recent attempts to overcome this weakness, we develop an enhanced tensor encoding model to build representations of word meaning for semantic processing. Our enhanced model demonstrates superior performance when compared to a robust baseline model on a number of semantic processing tasks.

Can you describe him for me? A technique for semantic person search in video

From a law enforcement standpoint, the ability to search for a person matching a semantic description (i.e. 1.8m tall, red shirt, jeans) is highly desirable. While a significant research effort has focused on person re-detection (the task of identifying a previously observed individual in surveillance video), these techniques require descriptors to be built from existing image or video observations. As such, person re-detection techniques are not suited to situations where footage of the person of interest is not readily available, such as a witness reporting a recent crime. In this paper, we present a novel framework that is able to search for a person based on a semantic description. The proposed approach uses size and colour cues, and does not require a person detection routine to locate people in the scene, improving utility in crowded conditions. The proposed approach is demonstrated with a new database that will be made available to the research community, and we show that the proposed technique is able to correctly localise a person in a video based on a simple semantic description.

Semantic judgement of medical concepts : combining syntagmatic and paradigmatic information with the tensor encoding model

This paper outlines a novel approach for modelling semantic relationships within medical documents. Medical terminologies contain a rich source of semantic information critical to a number of techniques in medical informatics, including medical information retrieval. Recent research suggests that corpus-driven approaches are effective at automatically capturing semantic similarities between medical concepts, thus making them an attractive option for accessing semantic information. Most previous corpus-driven methods only considered syntagmatic associations. In this paper, we adapt a recent approach that explicitly models both syntagmatic and paradigmatic associations. We show that the implicit similarity between certain medical concepts can only be modelled using paradigmatic associations. In addition, the inclusion of both types of associations overcomes the sensitivity to the training corpus experienced by previous approaches, making our method both more effective and more robust. This finding may have implications for researchers in the area of medical information retrieval.

Motorcycle Safety Research Project Interim Summary Report Research Deliverable 1: Investigate and Develop a Pre-learner Motorcycle Licensing Package

Motorcycle trauma is a serious road safety issue in Queensland and throughout Australia. In 2009, Queensland Transport (later Transport and Main Roads or TMR) appointed CARRS-Q to provide a three-year program of Road Safety Research Services for Motorcycle Rider Safety. Funding for this research originated from the Motor Accident Insurance Commission. This program of research was undertaken to produce knowledge to assist TMR to improve motorcycle safety by further strengthening the licensing and training system to make learner riders safer by developing a pre-learner package (Deliverable 1 which is the focus of this report), and by evaluating the Q-Ride CAP program to ensure that it is maximally effective and contributes to the best possible training for new riders (Deliverable 2), which is the focus of this report. Deliverable 3 of the program identified potential new licensing components that will reduce the incidence of risky riding and improve higher-order cognitive skills in new riders. While fatality and injury rates for learner car drivers are typically lower than for those with intermediate licences, this pattern is not found for learner motorcycle riders. Learner riders cannot be supervised as effectively as learner car drivers and errors are more likely to result in injury for learner riders than learner drivers. It is therefore imperative to improve safety for learner riders. Deliverable 1 examines the potential for improving the motorcycle learner and licence scheme by introducing a pre-learner motorcycle licensing and training scheme within Queensland. The tasks undertaken for Deliverable 1 were a literature review, analysis of learner motorcyclist crash and licensing data, and the development of a potential pre-learner motorcycle rider program.

Empirical analysis of the effect of dimension reduction and word order on semantic vectors

The aim of this paper is to provide a comparison of various algorithms and parameters to build reduced semantic spaces. The effect of dimension reduction, the stability of the representation and the effect of word order are examined in the context of the five algorithms bearing on semantic vectors: Random projection (RP), singular value decom- position (SVD), non-negative matrix factorization (NMF), permutations and holographic reduced representations (HRR). The quality of semantic representation was tested by means of synonym finding task using the TOEFL test on the TASA corpus. Dimension reduction was found to improve the quality of semantic representation but it is hard to find the optimal parameter settings. Even though dimension reduction by RP was found to be more generally applicable than SVD, the semantic vectors produced by RP are somewhat unstable. The effect of encoding word order into the semantic vector representation via HRR did not lead to any increase in scores over vectors constructed from word co-occurrence in context information. In this regard, very small context windows resulted in better semantic vectors for the TOEFL test.

Finding additional semantic entity information for search engines

Entity-oriented search has become an essential component of modern search engines. It focuses on retrieving a list of entities or information about the specific entities instead of documents. In this paper, we study the problem of finding entity related information, referred to as attribute-value pairs, that play a significant role in searching target entities. We propose a novel decomposition framework combining reduced relations and the discriminative model, Conditional Random Field (CRF), for automatically finding entity-related attribute-value pairs from free text documents. This decomposition framework allows us to locate potential text fragments and identify the hidden semantics, in the form of attribute-value pairs for user queries. Empirical analysis shows that the decomposition framework outperforms pattern-based approaches due to its capability of effective integration of syntactic and semantic features.

How activation, entanglement, and searching a semantic network contribute to event memory

Free association norms indicate that words are organized into semantic/associative neighborhoods within a larger network of words and links that bind the net together. We present evidence indicating that memory for a recent word event can depend on implicitly and simultaneously activating related words in its neighborhood. Processing a word during encoding primes its network representation as a function of the density of the links in its neighborhood. Such priming increases recall and recognition and can have long lasting effects when the word is processed in working memory. Evidence for this phenomenon is reviewed in extralist cuing, primed free association, intralist cuing, and single-item recognition tasks. The findings also show that when a related word is presented to cue the recall of a studied word, the cue activates it in an array of related words that distract and reduce the probability of its selection. The activation of the semantic network produces priming benefits during encoding and search costs during retrieval. In extralist cuing recall is a negative function of cue-to-distracter strength and a positive function of neighborhood density, cue-to-target strength, and target-to cue strength. We show how four measures derived from the network can be combined and used to predict memory performance. These measures play different roles in different tasks indicating that the contribution of the semantic network varies with the context provided by the task. We evaluate spreading activation and quantum-like entanglement explanations for the priming effect produced by neighborhood density.

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.

Modelling word activation in semantic networks : three scaled entanglement models compared

Modelling how a word is activated in human memory is an important requirement for determining the probability of recall of a word in an extra-list cueing experiment. Previous research assumed a quantum-like model in which the semantic network was modelled as entangled qubits, however the level of activation was clearly being over-estimated. This paper explores three variations of this model, each of which are distinguished by a scaling factor designed to compensate the overestimation.

Nonparametric semantic segmentation for 3D street scenes

In this paper we propose a method to generate a large scale and accurate dense 3D semantic map of street scenes. A dense 3D semantic model of the environment can significantly improve a number of robotic applications such as autonomous driving, navigation or localisation. Instead of using offline trained classifiers for semantic segmentation, our approach employs a data-driven, nonparametric method to parse scenes which easily scale to a large environment and generalise to different scenes. We use stereo image pairs collected from cameras mounted on a moving car to produce dense depth maps which are combined into a global 3D reconstruction using camera poses from stereo visual odometry. Simultaneously, 2D automatic semantic segmentation using a nonparametric scene parsing method is fused into the 3D model. Furthermore, the resultant 3D semantic model is improved with the consideration of moving objects in the scene. We demonstrate our method on the publicly available KITTI dataset and evaluate the performance against manually generated ground truth.

Going beyond ‘misfit’ as a reason for ERP package customisation

In an attempt to deal with the potential problems presented by existing information systems, a shift towards the implementation of ERP packages has been witnessed. The common view, particularly the one espoused by vendors, is that ERP packages are most successfully implemented when the standard model is adopted. Yet, despite this, customisation activity still occurs reportedly due to misalignment between the functionality of the package and the requirements of those in the implementing organisation. However, it is recognised that systems development and organisational decision-making are activities influenced by the perspectives of the various groups and individuals involved in the process. Thus, as customisation can be seen as part of systems development, and has to be decided upon, it should be thought about in the same way. In this study, two ERP projects are used to examine different reasons why customisation might take place. These reasons are then built upon through reference to the ERP and more general packaged software literature. The study suggests that whilst a common reason for customising ERP packages might be concerned with functionality misfits, it is important to look further into why these may occur, as there are clearly other reasons for customisation stemming from the multiplicity of social groups involved in the process.

The Australian clean energy package and the law of the world trade organisation : an analysis of compliance issues

This thesis is a study of whether the Australian Clean Energy Package complies with the rules of the World Trade Organization. It examines the legal framework for the Australian carbon pricing mechanism and related arrangements, using World Trade Organization law as the framework for analysis. In doing so, this thesis deconstructs the Clean Energy Package by considering the legal properties of eligible emissions units, the assistance measures introduced by the Package and the liabilities created by the carbon pricing mechanism.

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.

Biomechanical aspects of seating comfort in vehicle seating package engineering

In this paper, problems are described which are related to the ergonomic assessment of vehicle package design in vehicle systems engineering. The traditional approach, using questionnaire techniques for a subjective assessment of comfort related to package design, is compared to a biomechanical approach. An example is given for ingress design. The biomechanical approach is based upon objective postural data. The experimental setup for the study is described and methods used for the biomechanical analysis are explained. Because the biomechanic assessment requires not only a complex experimental setup but also time consuming data processing, a systematic reduction and preparation of biomechanic data for classification with an Artificial Neural Network significantly improves the economy of the biomechanical method.