ORCID Profile
0000-0002-1948-6819
Current Organisations
University of Western Australia
,
University of Sydney
,
University of Oxford
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
Publisher: Association for Computational Linguistics
Date: 2021
Publisher: ACM
Date: 30-04-2023
Publisher: No publisher found
Date: 2020
Publisher: Springer Berlin Heidelberg
Date: 2012
Publisher: No publisher found
Date: 2019
Publisher: ACM Press
Date: 2018
Publisher: Springer International Publishing
Date: 2016
Publisher: International Committee on Computational Linguistics
Date: 2020
Publisher: Springer Science and Business Media LLC
Date: 08-07-2021
DOI: 10.1038/S41586-021-03767-X
Abstract: The genetic make-up of an in idual contributes to the susceptibility and response to viral infection. Although environmental, clinical and social factors have a role in the chance of exposure to SARS-CoV-2 and the severity of COVID-19 1,2 , host genetics may also be important. Identifying host-specific genetic factors may reveal biological mechanisms of therapeutic relevance and clarify causal relationships of modifiable environmental risk factors for SARS-CoV-2 infection and outcomes. We formed a global network of researchers to investigate the role of human genetics in SARS-CoV-2 infection and COVID-19 severity. Here we describe the results of three genome-wide association meta-analyses that consist of up to 49,562 patients with COVID-19 from 46 studies across 19 countries. We report 13 genome-wide significant loci that are associated with SARS-CoV-2 infection or severe manifestations of COVID-19. Several of these loci correspond to previously documented associations to lung or autoimmune and inflammatory diseases 3–7 . They also represent potentially actionable mechanisms in response to infection. Mendelian randomization analyses support a causal role for smoking and body-mass index for severe COVID-19 although not for type II diabetes. The identification of novel host genetic factors associated with COVID-19 was made possible by the community of human genetics researchers coming together to prioritize the sharing of data, results, resources and analytical frameworks. This working model of international collaboration underscores what is possible for future genetic discoveries in emerging pandemics, or indeed for any complex human disease.
Publisher: Springer International Publishing
Date: 2019
Publisher: Elsevier BV
Date: 06-2018
Publisher: Springer International Publishing
Date: 2020
Publisher: ACM
Date: 26-10-2021
Publisher: Springer Science and Business Media LLC
Date: 12-03-2022
DOI: 10.1007/S10115-022-01665-W
Abstract: As an essential component of human cognition, cause–effect relations appear frequently in text, and curating cause–effect relations from text helps in building causal networks for predictive tasks. Existing causality extraction techniques include knowledge-based, statistical machine learning (ML)-based, and deep learning-based approaches. Each method has its advantages and weaknesses. For ex le, knowledge-based methods are understandable but require extensive manual domain knowledge and have poor cross-domain applicability. Statistical machine learning methods are more automated because of natural language processing (NLP) toolkits. However, feature engineering is labor-intensive, and toolkits may lead to error propagation. In the past few years, deep learning techniques attract substantial attention from NLP researchers because of its powerful representation learning ability and the rapid increase in computational resources. Their limitations include high computational costs and a lack of adequate annotated training data. In this paper, we conduct a comprehensive survey of causality extraction. We initially introduce primary forms existing in the causality extraction: explicit intra-sentential causality, implicit causality, and inter-sentential causality. Next, we list benchmark datasets and modeling assessment methods for causal relation extraction. Then, we present a structured overview of the three techniques with their representative systems. Lastly, we highlight existing open challenges with their potential directions.
Publisher: No publisher found
Date: 2016
Publisher: Springer Berlin Heidelberg
Date: 2012
Publisher: Springer International Publishing
Date: 2023
Publisher: Springer International Publishing
Date: 2015
Publisher: Springer International Publishing
Date: 2016
Publisher: Springer Science and Business Media LLC
Date: 02-07-2016
Publisher: Springer Berlin Heidelberg
Date: 2012
Publisher: International Committee on Computational Linguistics
Date: 2020
Publisher: ACM
Date: 27-02-2023
Publisher: ACM
Date: 21-10-2023
Publisher: ISCA
Date: 30-08-2021
Publisher: IEEE
Date: 06-2012
Publisher: Springer Science and Business Media LLC
Date: 07-03-2022
DOI: 10.1038/S41586-022-04576-6
Abstract: Critical COVID-19 is caused by immune-mediated inflammatory lung injury. Host genetic variation influences the development of illness requiring critical care 1 or hospitalization 2–4 after infection with SARS-CoV-2. The GenOMICC (Genetics of Mortality in Critical Care) study enables the comparison of genomes from in iduals who are critically ill with those of population controls to find underlying disease mechanisms. Here we use whole-genome sequencing in 7,491 critically ill in iduals compared with 48,400 controls to discover and replicate 23 independent variants that significantly predispose to critical COVID-19. We identify 16 new independent associations, including variants within genes that are involved in interferon signalling ( IL10RB and PLSCR1 ), leucocyte differentiation ( BCL11A ) and blood-type antigen secretor status ( FUT2 ). Using transcriptome-wide association and colocalization to infer the effect of gene expression on disease severity, we find evidence that implicates multiple genes—including reduced expression of a membrane flippase ( ATP11A ), and increased expression of a mucin ( MUC1 )—in critical disease. Mendelian randomization provides evidence in support of causal roles for myeloid cell adhesion molecules ( SELE , ICAM5 and CD209 ) and the coagulation factor F8 , all of which are potentially druggable targets. Our results are broadly consistent with a multi-component model of COVID-19 pathophysiology, in which at least two distinct mechanisms can predispose to life-threatening disease: failure to control viral replication or an enhanced tendency towards pulmonary inflammation and intravascular coagulation. We show that comparison between cases of critical illness and population controls is highly efficient for the detection of therapeutically relevant mechanisms of disease.
Publisher: ACM
Date: 11-07-2021
Publisher: Springer Science and Business Media LLC
Date: 04-06-2013
Publisher: Association for Computing Machinery (ACM)
Date: 23-12-2023
DOI: 10.1145/3547138
Abstract: Intent classification, to identify the speaker’s intention, and slot filling, to label each token with a semantic type, are critical tasks in natural language understanding. Traditionally the two tasks have been addressed independently. More recently joint models that address the two tasks together have achieved state-of-the-art performance for each task and have shown there exists a strong relationship between the two. In this survey, we bring the coverage of methods up to 2021 including the many applications of deep learning in the field. As well as a technological survey, we look at issues addressed in the joint task and the approaches designed to address these issues. We cover datasets, evaluation metrics, and experiment design and supply a summary of reported performance on the standard datasets.
Publisher: Agora University of Oradea
Date: 13-04-2018
DOI: 10.15837/IJCCC.2018.2.3189
Abstract: Preventive maintenance is required in large scale industries to facilitate highly efficient performance. The efficiency of production can be maximized by preventing the failure of facilities in advance. Typically, regular maintenance is conducted manually in which case, it is hard to prevent repeated failures. Also, since measures to prevent failure depend on proactive problem-solving by the facility expert, they have limitations when the expert is absent, or any error in diagnosis is made by an unskilled expert. In many cases, an alarm system is used to aid manual facility diagnosis and early detection. However, it is not efficient in practice, since it is designed to simply collect information and is activated even with small problems. In this paper, we designed and developed an automated preventive maintenance system using experts’ experience in detecting failure, determining the cause, and predicting future system failure. There are two main functions in order to acquire and analyze domain expertise. First, we proposed the network-based process map that can extract the expert’s knowledge of the written failure report. Secondly, we designed and implemented an incremental learning rule-based expert system with alarm data and failure case. The evaluation results shows that the combination of two main functions works better than another failure diagnosis and prediction frameworks.
Publisher: Springer Berlin Heidelberg
Date: 2012
Publisher: Springer International Publishing
Date: 2016
Publisher: Springer International Publishing
Date: 2016
Publisher: ACM
Date: 21-10-2023
Publisher: International Joint Conferences on Artificial Intelligence Organization
Date: 07-2022
Abstract: Pretrained models have produced great success in both Computer Vision (CV) and Natural Language Processing (NLP). This progress leads to learning joint representations of vision and language pretraining by feeding visual and linguistic contents into a multi-layer transformer, Visual-Language Pretrained Models (VLPMs). In this paper, we present an overview of the major advances achieved in VLPMs for producing joint representations of vision and language. As the preliminaries, we briefly describe the general task definition and genetic architecture of VLPMs. We first discuss the language and vision data encoding methods and then present the mainstream VLPM structure as the core content. We further summarise several essential pretraining and fine-tuning strategies. Finally, we highlight three future directions for both CV and NLP researchers to provide insightful guidance.
Publisher: Springer International Publishing
Date: 2014
Publisher: Frontiers Media SA
Date: 24-04-2023
DOI: 10.3389/FDGTH.2023.1154133
Abstract: Drug-drug interaction (DDI) may lead to adverse reactions in patients, thus it is important to extract such knowledge from biomedical texts. However, previously proposed approaches typically focus on capturing sentence-aspect information while ignoring valuable knowledge concerning the whole corpus. In this paper, we propose a Mu lti-aspect G raph-based DDI extraction model, named DDI-MuG. We first employ a bio-specific pre-trained language model to obtain the token contextualized representations. Then we use two graphs to get syntactic information from input instance and word co-occurrence information within the entire corpus, respectively. Finally, we combine the representations of drug entities and verb tokens for the final classification To validate the effectiveness of the proposed model, we perform extensive experiments on two widely used DDI extraction dataset, DDIExtraction-2013 and TAC 2018. It is encouraging to see that our model outperforms all twelve state-of-the-art models. In contrast to the majority of earlier models that rely on the black-box approach, our model enables visualization of crucial words and their interrelationships by utilizing edge information from two graphs. To the best of our knowledge, this is the first model that explores multi-aspect graphs to the DDI extraction task, and we hope it can establish a foundation for more robust multi-aspect works in the future.
Publisher: ACM
Date: 18-07-2023
Publisher: Springer International Publishing
Date: 2022
Publisher: Springer Berlin Heidelberg
Date: 2012
Publisher: Springer Berlin Heidelberg
Date: 2012
Publisher: Springer International Publishing
Date: 2014
Publisher: Springer Science and Business Media LLC
Date: 03-08-2013
Publisher: Association for Computational Linguistics
Date: 2022
Publisher: No publisher found
Date: 2016
Publisher: Springer Berlin Heidelberg
Date: 2012
Publisher: MDPI AG
Date: 07-08-2023
Abstract: Visual Question Answering (VQA) models fail catastrophically on questions related to the reading of text-carrying images. However, TextVQA aims to answer questions by understanding the scene texts in an image–question context, such as the brand name of a product or the time on a clock from an image. Most TextVQA approaches focus on objects and scene text detection, which are then integrated with the words in a question by a simple transformer encoder. The focus of these approaches is to use shared weights during the training of a multi-modal dataset, but it fails to capture the semantic relations between an image and a question. In this paper, we proposed a Scene Graph-Based Co-Attention Network (SceneGATE) for TextVQA, which reveals the semantic relations among the objects, the Optical Character Recognition (OCR) tokens and the question words. It is achieved by a TextVQA-based scene graph that discovers the underlying semantics of an image. We create a guided-attention module to capture the intra-modal interplay between the language and the vision as a guidance for inter-modal interactions. To permit explicit teaching of the relations between the two modalities, we propose and integrate two attention modules, namely a scene graph-based semantic relation-aware attention and a positional relation-aware attention. We conduct extensive experiments on two widely used benchmark datasets, Text-VQA and ST-VQA. It is shown that our SceneGATE method outperforms existing ones because of the scene graph and its attention modules.
Publisher: No publisher found
Date: 2016
Publisher: Frontiers Media SA
Date: 17-02-2021
DOI: 10.3389/FDGTH.2021.602683
Abstract: Family and Domestic violence (FDV) is a global problem with significant social, economic, and health consequences for victims including increased health care costs, mental trauma, and social stigmatization. In Australia, the estimated annual cost of FDV is $22 billion, with one woman being murdered by a current or former partner every week. Despite this, tools that can predict future FDV based on the features of the person of interest (POI) and victim are lacking. The New South Wales Police Force attends thousands of FDV events each year and records details as fixed fields (e.g., demographic information for in iduals involved in the event) and as text narratives which describe abuse types, victim injuries, threats, including the mental health status for POIs and victims. This information within the narratives is mostly untapped for research and reporting purposes. After applying a text mining methodology to extract information from 492,393 FDV event narratives (abuse types, victim injuries, mental illness mentions), we linked these characteristics with the respective fixed fields and with actual mental health diagnoses obtained from the NSW Ministry of Health for the same cohort to form a comprehensive FDV dataset. These data were input into five deep learning models (MLP, LSTM, Bi-LSTM, Bi-GRU, BERT) to predict three FDV offense types (“hands-on,” “hands-off,” “Apprehended Domestic Violence Order (ADVO) breach”). The transformer model with BERT embeddings returned the best performance (69.00% accuracy 66.76% ROC) for “ADVO breach” in a multilabel classification setup while the binary classification setup generated similar results. “Hands-off” offenses proved the hardest offense type to predict (60.72% accuracy 57.86% ROC using BERT) but showed potential to improve with fine-tuning of binary classification setups. “Hands-on” offenses benefitted least from the contextual information gained through BERT embeddings in which MLP with categorical embeddings outperformed it in three out of four metrics (65.95% accuracy 78.03% F1-score 70.00% precision). The encouraging results indicate that future FDV offenses can be predicted using deep learning on a large corpus of police and health data. Incorporating additional data sources will likely increase the performance which can assist those working on FDV and law enforcement to improve outcomes and better manage FDV events.
Publisher: Springer Berlin Heidelberg
Date: 2011
Publisher: No publisher found
Date: 2016
Publisher: Elsevier BV
Date: 2018
DOI: 10.1016/J.IJMEDINF.2017.11.004
Abstract: Medical students should be able to actively apply clinical reasoning skills to further their interpretative, diagnostic, and treatment skills in a non-obtrusive and scalable way. Case-Based Learning (CBL) approach has been receiving attention in medical education as it is a student-centered teaching methodology that exposes students to real-world scenarios that need to be solved using their reasoning skills and existing theoretical knowledge. In this paper, we propose an interactive CBL System, called iCBLS, which supports the development of collaborative clinical reasoning skills for medical students in an online environment. The iCBLS consists of three modules: (i) system administration (SA), (ii) clinical case creation (CCC) with an innovative semi-automatic approach, and (iii) case formulation (CF) through intervention of medical students' and teachers' knowledge. Two evaluations under the umbrella of the context/input rocess roduct (CIPP) model have been performed with a Glycemia study. The first focused on the system satisfaction, evaluated by 54 students. The latter aimed to evaluate the system effectiveness, simulated by 155 students. The results show a high success rate of 70% for students' interaction, 76.4% for group learning, 72.8% for solo learning, and 74.6% for improved clinical skills.
Publisher: ACM
Date: 30-01-2018
Location: United Kingdom of Great Britain and Northern Ireland
Location: United Kingdom of Great Britain and Northern Ireland
Location: United Kingdom of Great Britain and Northern Ireland
Start Date: 2015
End Date: 2016
Funder: University of Tasmania
View Funded ActivityStart Date: 2016
End Date: 2017
Funder: Asian Office of Aerospace Research & Development
View Funded ActivityStart Date: 2016
End Date: 2016
Funder: Office of Naval Research Global
View Funded ActivityStart Date: 2016
End Date: 2017
Funder: Hyundai MNSOFT Inc.
View Funded Activity