Computing and Mathematical Sciences Papers: Recently added
Now showing items 1-20 of 1458
-
PolyLM: Learning about polysemy through language modeling
(ACL, 2021)To avoid the “meaning conflation deficiency” of word embeddings, a number of models have aimed to embed individual word senses. These methods at one time performed well on tasks such as word sense induction (WSI), but they ... -
Bundle-driven metadiscourse analysis: Sentence initial bundles in Chinese and New Zealand postgraduates' thesis writing
(Peter Lang, 2017)Metadiscourse and lexical bundles are two closely related concepts and both operate as overlapping functional units in texts. Metadiscourse analysis always takes a top-down approach, in which discourse analysts begin from ... -
A comparison of verilog synthesis frontends
(The International Academy, Research and Industry Association (IARIA), 2021)A crucial consideration in choosing a frontend synthesis tool is the quality of the synthesised result. This kind of benchmarking is critical to choosing a fit-for-purpose tool. However, to the best of the authors’ knowledge, ... -
Reflections on remixing open access content into open educational resources: A new paradigm for sustainable data-driven language learning systems design in higher education
(Springer, 2023)This chapter presents a new paradigm for sustainable data – driven language learning systems design in higher education that draws on qualitative reflections spanning a decade (2012–2022) with stakeholders from an ongoing ... -
Modelling a blockchain for smart contract verification using DeepSEA
(Association for Computing Machinery, 2022)To create trustworthy programs, the 'gold standard' is specifications at a high-enough level to clearly correspond to the informal specifications, and also a refinement proof linking these high-level specifications down ... -
Provably correct smart contracts: An approach using DeepSEA
(Association for Computing Machinery, 2022)It is possible to download a piece of software over the internet and then verify its correctness locally using an appropriate trusted proof system. However, on a blockchain like Ethereum, smart contracts cannot be altered ... -
Experiments in cross-domain few-shot learning for image classification: extended abstract
(PMLR, 2022)We summarise experiments (Wang et al., 2022) evaluating cross-domain few-shot learning (CDFSL) with feature extractors trained on ImageNet. The work explores the transfer performance of extracted features on five target ... -
Prevalence of sociodemographic factors in a cohort of diabetes mellitus: A retrospective study
(ACM, 2022)Exploring the sociodemographic factors of a cohort is a vital phase in revealing significant aspects of the societal health status. The health care sector utilises the results of exploratory analysis of the sociodemographic ... -
Showcasing the TAIAO project: providing resources for machine learning from images of New Zealand's natural environment
(Informa UK Limited, 2022)Proper management of the earth's natural resources is imperative to combat further degradation of the natural environment. However, the environmental datasets necessary for informed resource planning and conservation can ... -
Large scale K-means clustering using GPUs
(Springer Science and Business Media LLC, 2022)The k-means algorithm is widely used for clustering, compressing, and summarizing vector data. We present a fast and memory-efficient GPU-based algorithm for exact k-means, Asynchronous Selective Batched K-means (ASB ... -
Learning to extract geographic information from internet router hostnames
(ACM, 2021)Geolocating Internet routers is a long-standing and notoriously difficult challenge, and current solutions lack the accuracy and adaptability to yield reliable results. We revisit this problem, designing a solution capable ... -
Patient-reported diagnostic intervals to colorectal cancer diagnosis in the Midland region of New Zealand: a prospective cohort study
(Oxford University Press, 2021)Background and objectives New Zealand (NZ) has high rates of colorectal cancer (CRC) but low rates of early detection. The majority of CRC is diagnosed through general practice, where lengthy diagnostic intervals are ... -
Analyzing and repairing concept drift adaptation in data stream classification
(2021)Data collected over time often exhibit changes in distribution, or concept drift, caused by changes in factors relevant to the classification task, e.g. weather conditions. Incorporating all relevant factors into the model ... -
Surgical tool datasets for machine learning research: A survey
(Springer, 2022)This paper is a comprehensive survey of datasets for surgical tool detection and related surgical data science and machine learning techniques and algorithms. The survey offers a high level perspective of current research ... -
Evaluation of deep learning techniques on a novel hierarchical surgical tool dataset
(Springer Nature Switzerland AG, 2022)A new hierarchically organised dataset for artificial intelligence and machine learning research is presented, focusing on intelligent management of surgical tools. In addition to 360 surgical tool classes, we create a ... -
Children’s query formulation and search result exploration
(Springer Science and Business Media LLC, 2021)Our research aims at understanding children’s information search and their use of information search tools during educational pursuits. We conducted an observation study with 50 New Zealand school children between the ages ... -
A study of mobile app use for teaching and research in higher education
(Springer Science and Business Media LLC, 2022)The exponential growth in the use of digital technologies and the availability of mobile software applications (apps) has been well documented over the past decade. Literature on the integration of mobile technology into ... -
Mobile app development: Work-integrated learning collaborations with Māori and Fijian partners
(2022)Only a few information and communication technology (ICT) work-integrated learning (WIL) projects involving universities and Indigenous partners are being reported and very little is known about the approaches that are ... -
Physical metadata visualisation: The knitted personal library
(ACM, 2022)Personal collections, be they books, music, or artefacts have significance to the owner, and provide conversation and engagement with visitors. For example visitors of physical libraries may browse the spines, select a ... -
Efficiently correcting machine learning: considering the role of example ordering in human-in-the-loop training of image classification models
(ACM, 2022)Arguably the most popular application task in artificial intelligence is image classification using transfer learning. Transfer learning enables models pre-trained on general classes of images, available in large numbers, ...
