Project Description
In the near future, all public hospitals in Queensland will share one integrated Electronic Medical Record (iEMR). It contains an extensive and rich repository of structured and unstructured information that could be used to facilitate clinical practice improvement and clinical research. However, it is extremely difficult and labour intensive to access this data in order to use it for these purposes. This research project will streamline this process that will not only be useful within Queensland, but to all health care providers that use similar EMRs, worldwide. The project will develop a new, efficient capability for data extraction from the ieMR. We will construct a robust data model from the existing iEMR database that collates and indexes information from both the existing structured query language (SQL) fields and currently unindexed, but invaluable unstructured information.
The successful applicant will enrol through the School of Information Technology and Electrical Engineering at The University of Queensland (UQ), and will be a member of the ielab team (www.ielab.io), within the UQ Data Science discipline.
The Data Science discipline researches and develops innovative and practical solutions for business, scientific and social applications in the realm of big data. The group encompasses a variety of research strengths including: Data and knowledge engineering, Information Retrieval, Computer Vision, and Complex and Intelligent Systems. You will join a world-leading research group currently composed of 13 academic staff members (including 4 full professors, two DECRA fellows and an Advanced Queensland Fellow), 7 research fellows and over 40 PhD students. Members of the group have a successful track record of publishing in top conferences and journals such as ACM SIGIR, ACM CIKM, The Web Conference (WWW), SIGMOD, VLDB, ICDE, ICDM, KDD and various ACM and IEEE transactions.
The research environment available to the project is world-class. The University of Queensland (UQ) has a strong and internationally focused research culture. It is ranked in the top 1% of world universities in three widely publicized international University rankings. The areas of research in these PhD projects have a strategic fit within UQ’s existing research strengths in Data Science.
Brisbane is a liveable, capital city with great weather, vibrant green spaces, lively bars and restaurants, world-class art galleries and premier events. It is the third most populous city in Australia and is closed to premier recreational locations such as the Sunshine Coast and the Gold Coast.
Successful applicants should possess a PhD in the field of Information Retrieval, Natural Language Processing, or Machine Learning on Textual Data.
POSITION NOW FILLED
Project Description
Valuable grains R&D output is currently locked away into project reports, communications and scientific publications. This text-based information is not easily discoverable and synthesised. Thus growers are not able to put into practice these valuable insights. This project will develop a conversational agent (AskAg) that will provide personalised access to this valuable information leading directly to better, data-driven growing decisions. Through question-answering systems, AgAsk will elicit and understand growers information needs and preferences, providing contextualised access to insights in Ag R&D. AgAsk will use state-of-the-art IR, NLP and ML technology to interpret natural language questions. Ag R&D resources will be mined from textual information and converted into a knowledge graph capturing key agricultural concepts and relations (e.g. protozoa –effective_for–> control of pest molluscs). AgAsk will use this knowledge graph to formulate contextualised and interpretable answers to a growers question (e.g. via abstractive summarisation and answer generation).
The successful applicant will enrol through the School of Information Technology and Electrical Engineering at The University of Queensland (UQ), and will be a member of the ielab team (www.ielab.io), within the UQ Data Science discipline.
The Data Science discipline researches and develops innovative and practical solutions for business, scientific and social applications in the realm of big data. The group encompasses a variety of research strengths including: Data and knowledge engineering, Information Retrieval, Computer Vision, and Complex and Intelligent Systems. You will join a world-leading research group currently composed of 13 academic staff members (including 4 full professors, two DECRA fellows and an Advanced Queensland Fellow), 7 research fellows and over 40 PhD students. Members of the group have a successful track record of publishing in top conferences and journals such as ACM SIGIR, ACM CIKM, The Web Conference (WWW), SIGMOD, VLDB, ICDE, ICDM, KDD and various ACM and IEEE transactions.
The research environment available to the project is world-class. The University of Queensland (UQ) has a strong and internationally focused research culture. It is ranked in the top 1% of world universities in three widely publicized international University rankings. The areas of research in these PhD projects have a strategic fit within UQ’s existing research strengths in Data Science.
Brisbane is a liveable, capital city with great weather, vibrant green spaces, lively bars and restaurants, world-class art galleries and premier events. It is the third most populous city in Australia and is closed to premier recreational locations such as the Sunshine Coast and the Gold Coast.
Successful applicants should possess a PhD in the field of Information Retrieval, Natural Language Processing, or Machine Learning on Textual Data.
You should have demonstrated expert knowledge in relevant empirical research methods, including Knowledge Graph creation, question answering, answer generation and ranking, abstractive summarisation, interactive information retrieval, intent understanding, user-based evaluation (evaluation of IR systems with users). Research experience with conversational search and conversational agents, domain-specific search, and task-based retrieval will be beneficial and highly regarded. You would have a demonstrated publication record in quality research outlets in relevant fields; examples include ACM SIGIR, ACM WSDM, The Web Conf, ACL, NAACL-HLT, EMNLP, AAAI, ACM TOIS, ACM TIST, TACL. You would also have showcased ability to successfully work in a research team to deliver outputs to industry and outstanding effective communication and interpersonal skills.
Project Description
This project aims to help people make better health decisions from search engines. 80% of Australians use Dr Google despite evidence showing that many often find incorrect and unreliable health information, which can increase the severity of their health condition, ultimately increasing cost of healthcare delivery.
This project expects to provide new understanding about why and how people fail to find useful health information. Expected outcomes of this project are new models and methods for evaluating high-stakes search and new search technologies to help people find and recognise high quality information to make better health decisions. This should provide significant benefits to Australian health consumers and the healthcare system.
Directions for research in this project include, but are not limited to:
The successful applicant will enrol through the School of Information Technology and Electrical Engineering at The University of Queensland (UQ), and will be a member of the ielab team (www.ielab.io), within the UQ Data Science group. The Data Science group researches and develops innovative and practical solutions for business, scientific and social applications in the realm of big data. The group encompasses a variety of research strengths including: Data and knowledge engineering, Information Retrieval, Computer Vision, and Complex and Intelligent Systems. You will join a world-leading research group currently composed of 13 academic staff members (including 4 full professors, two DECRA fellows and an Advanced Queensland Fellow), 7 research fellows and over 40 PhD students. Members of the group have a successful track record of publishing in top conferences and journals such as ACM SIGIR, ACM CIKM, The Web Conference (WWW), SIGMOD, VLDB, ICDE, ICDM, KDD and various ACM and IEEE transactions. The research environment available to the project is world-class. The University of Queensland (UQ) has a strong and internationally focused research culture. It is ranked in the top 1% of world universities in three widely publicized international University rankings. The areas of research in these PhD projects have a strategic fit within UQ’s existing research strengths in Data Science. Brisbane is a liveable, capital city with great weather, vibrant green spaces, lively bars and restaurants, world-class art galleries and premier events. It is the third most populous city in Australia and is closed to premier recreational locations such as the Sunshine Coast and the Gold Coast.
The successful candidate must commence by Research Quarter 1, 2020 (January).
Educational background
Computer Science, Information Retrieval, Artificial Intelligence, Machine Learning, Natural Language Processing.
How do I express my interest to apply?
Interested? Contact the Chief Investigator, Dr. Guido Zuccon by email at g.zuccon@uq.edu.au by October 10, 2019 to express your interest. In your email, include:
More information about the application process once preliminary selection has taken place can be found at https://scholarships.uq.edu.au/scholarship/grant-aligned-priority-phd-scholarships.
POSITION NOW FILLED
]]>The following tutorial was also accepted for publication:
The details of this tutorial can be found here.
]]>The presentations include a live demonstration of the two systems. These demonstrations are run in the open source searchrefiner system.
]]>This project aims to explore automated processes to learn high quality Knowledge Graphs from various medical data including textbooks, journals, trusted web content, and electronic medical records, principally in Chinese. Natural language processing and statistical analysis will be applied to extract medical entities such as symptoms, diseases, drugs, etc. from unstructured and semi-structured data, as well as correlation and causation between these entities. This will be the first step towards developing learning models that perform diagnostic inference directly on top of the automatically built health knowledge graphs.
Successful applicants will have a bachelor degree (with honours – or equivalent degree, including Masters) in Computer Science or related field; solid programming and algorithmic skills. Preferred, but not essential: knowledge of Information Retrieval, Natural Language Processing, Machine Learning, demonstrated by relevant experience, courses or publications.
To be considered for this scholarship, please email the following documents to Dr Wen Hua (w.hua@uq.edu.au) and Dr Guido Zuccon (g.zuccon@uq.edu.au)
Please note the following: Submitting the above documents does not constitute a full application for admission into The University of Queensland’s PhD program.
This project aims to develop a unified framework to automate manual diseases diagnosis by addressing key research challenges in medical image analysis:
1) improving the quality and speed of medical image annotations;
2) transferring knowledge of different imaging procedures;
3) building medical imaging datasets using active learning; and
4) providing accurate segmentation/localization of objects/areas-of-interest boundaries in medical images.
Successful applicants will have a bachelor degree (with honours – or equivalent degree, including Masters) in Computer Science or Electrical Engineering or Biomedical Engineering or Physics, or a related field; solid programming and algorithmic skills. Preferred, but not essential: in-depth knowledge of machine learning techniques, particularly deep learning demonstrated by relevant experience, courses or publications; hands-on experience with one or more deep learning libraries (Torch, Tensorflow, Theano, Caffe, etc.); in-depth knowledge of computer vision methods and algorithms.
To be considered for this scholarship, please email the following documents to Dr Mahsa Baktashmotlagh (m.baktashmotlagh@uq.edu.au) and Dr Guido Zuccon (g.zuccon@uq.edu.au)
Please note the following: Submitting the above documents does not constitute a full application for admission into The University of Queensland’s PhD program.
This project aims to design and experimentally evaluate novel human-in-the-loop techniques to support and improve the results of data-driven algorithms on data in Chinese. For example, you will investigate:
1) the use of human feedback to improve the quality of automatic medical entity relationship extraction and knowledge graph construction;
2) improving the use of manual annotations to support AI methods for medical image processing (also in combination with active learning);
3) designing novel task routing algorithms to assign a manual data labelling task to the right medical expert, considering at the same time (a) the cost to access experts, (b) the skills required to complete the task, and (c) the task priority; and
4) task design strategies that can minimise the time required by medical experts to complete the task effectively.
Successful applicants will have a bachelor degree (with honours – or equivalent degree, including Masters) in Computer Science or related field; solid programming and algorithmic skills. Preferred, but not essential: knowledge of Information Retrieval, Natural Language Processing, Machine Learning, demonstrated by relevant experience, courses or publications.
To be considered for this scholarship, please email the following documents to Dr Gianluca Demartini (g.demartini@uq.edu.au) and Dr Guido Zuccon (g.zuccon@uq.edu.au)
Please note the following: Submitting the above documents does not constitute a full application for admission into The University of Queensland’s PhD program.
#########################################################################
These projects will be part of the new University of Queensland’s Health Data Science research lab created in collaboration with industry partners. The new research lab is part of the Data Science Research Group (https://www.itee.uq.edu.au/research/data-science), Information Technology and Electrical Engineering School, at the University of Queensland located in Brisbane, Australia.
The Data Science group researches and develops innovative and practical solutions for business, scientific and social applications in the realm of big data. The group encompasses a variety of research strengths including: Data and knowledge engineering, Information Retrieval, Computer Vision, and Complex and Intelligent Systems. You will join a world-leading research group currently composed of 13 academic staff members (including 4 full professors, two DECRA fellows and an Advanced Queensland Fellow), 7 research fellows and over 40 PhD students. Members of the group have a successful track record of publishing in top conferences and journals such as ACM SIGIR, ACM CIKM, The Web Conference (WWW), SIGMOD, VLDB, ICDE, ICDM, KDD, CVPR, ICCV, ICML, PAMI, JMLR, ICLR and various ACM and IEEE transactions.
The research environment available to the project is world-class. The University of Queensland (UQ) has a strong and internationally focused research culture. It is ranked in the top 1% of world universities in three widely publicized international University rankings. The areas of research in these PhD projects have a strategic fit within UQ’s existing research strengths in Data Science.
Brisbane is a liveable, capital city with great weather, vibrant green spaces, lively bars and restaurants, world-class art galleries and premier events. It is the third most populous city in Australia and is closed to premier recreational locations such as the Sunshine Coast and the Gold Coast.
Expected start for all projects: April or July 2019
POSITIONS NOW FILLED
]]>The abstract of the journal article is made available below.
]]>Background: Understandability plays a key role in ensuring that people accessing health information are capable of gaining insights that can assist them with their health concerns and choices. The access to unclear or misleading information has been shown to negatively impact the health decisions of the general public.
Objective: The aim of this study was to investigate methods to estimate the understandability of health Web pages and use these to improve the retrieval of information for people seeking health advice on the Web.
Methods: Our investigation considered methods to automatically estimate the understandability of health information in Web pages, and it provided a thorough evaluation of these methods using human assessments as well as an analysis of preprocessing factors affecting understandability estimations and associated pitfalls. Furthermore, lessons learned for estimating Web page understandability were applied to the construction of retrieval methods, with specific attention to retrieving information understandable by the general public.
Results: We found that machine learning techniques were more suitable to estimate health Web page understandability than traditional readability formulae, which are often used as guidelines and benchmark by health information providers on the Web (larger difference found for Pearson correlation of .602 using gradient boosting regressor compared with .438 using Simple Measure of Gobbledygook Index with the Conference and Labs of the Evaluation Forum eHealth 2015 collection).
Conclusions: The findings reported in this paper are important for specialized search services tailored to support the general public in seeking health advice on the Web, as they document and empirically validate state-of-the-art techniques and settings for this domain application.
"Automatic Boolean Query Refinement for Systematic Review Literature Search" accepted as full paper at @TheWebConf (WWW'19) -- by @IELabGroup 's researchers @hscells @guidozuc and @bevan_koopman #UQIR #automationsystematicreviews
— Guido Zuccon (@guidozuc) 21 January 2019
announcement on twitter
]]>