Application Form
PhD Studentship in User-centric Multimodal Knowledge Graph Support Systems [Phd_KGSS_RBGJ_UCD]

JobRef: 18627
  • Accepted file types: pdf, Max. file size: 12 MB.
  • Accepted file types: pdf, Max. file size: 2 MB.

PhD Studentship in User-centric Multimodal Knowledge Graph Support Systems [Phd_KGSS_RBGJ_UCD]

Level:PhD
POSTED:July 19, 2022
LOCATION:University College Dublin
CLOSES:August 7, 2022
Duration:4 Years
Reports to:Prof Rob Brennan & Prof Gareth Jones
Salary:€18,500 (Annual Stipend + University Fees)
Closing Date:August 7, 2022

Why ADAPT?

  • Contribute to the ADAPT research agenda that pioneers and combines research in AI driven technologies: Natural Language Processing, Video/Text/Image/Speech processing, digital engagement & HCI, semantic modeling, personalisation, privacy & data governance. 
  • Work with our interdisciplinary team of  leading experts from the complementary fields of, Social Sciences,  Communications, Commerce/Fintech, Ethics, Law,  Health, Environment and Sustainability.
  • Leverage our success.  ADAPT’s researchers have signed 43 collaborative research projects, 52 licence agreements and oversee 16 active commercialisation funds and 52 commercialisation awards.  ADAPT has won 40 competitive EU research projects and obtained €18.5 million in non-exchequer non-commercial funding. Additionally, six spinout companies have been formed. ADAPT’s researchers have produced over 1,500 journal and conference publications and nearly 100 PhD students have been trained. 

 

As an ADAPT funded PhD researcher you will have access to a network of 85 global experts and over 250 staff as well as a wide multi-disciplinary ecosystem across 8 leading Irish universities. We can influence and inform your work, share our networks and collaborate with you to increase your impact, and accelerate your career opportunities. Specifically we offer: 

  1. Opportunity to build your profile at international conferences and global events.
  2. A solid career pathway through formalised training & development, expert one-on-one supervision and exposure to top specialists.
  3. A Fully funded, 4 year PhD postgraduate studentship which includes  a stipend of (€18,500 per annum – non taxed), along with equipment, annual travel funding 
  4. Funding for annual fees

 

Research Topic 

Knowledge graphs provide  repositories of explainable descriptions of real world situations.  They represent the key features of data collections, and can be used in tasks such as classification, recommendation, analysis or question answering. They are now increasingly being used in AI systems to tackle data sparsity and cold start problems. The scale and scope of knowledge graphs continues to increase with  graphs themselves becoming rich multimodal knowledge stores, containing  text, images and other media alongside formalised facts. These rich repositories are creating new opportunities for using knowledge in novel ways in a wide variety of applications. However, to realize the potential of this new generation of knowledge graphs, new techniques drawing on information retrieval, natural language processing and data science are needed to help users or agents to effectively query the graphs to identify key knowledge patterns, to rank or to compare entities. 

This PhD aims to devise new techniques to help users to identify significant patterns in longitudinal knowledge graphs describing healthcare settings. For example repeating events representing key institutional capabilities or vital institutional knowledge for safety management applications. New methods and tools will be developed for multimodal graph comparison, dialog-based user support for mining insights from knowledge graphs and automated query extraction. This research will be aligned with the EU guidelines on trustworthy AI and leverage a mix of information retrieval, natural language processing, knowledge graphs and user-centric systems research techniques. This work will push the boundaries of querying for multi-modal knowledge graphs, knowledge entity ranking and recommendation, graph comparison to unstructured open knowledge and documents. This PhD will feature collaboration with our industry partners in health information systems, aviation, and risk management and so equip the successful candidate for career paths in both industry and academia. 

The successful candidate will work within a large group of academics, postdoctoral researchers and PhD students and will be part of both the Transparent Digital Governance and the Digitally Enhanced Engagement research strands of the ADAPT Centre under the supervision of Dr Rob Brennan in University College Dublin and Prof Gareth Jones in Dublin City University.

As part of this studentship, the successful candidate  will have the opportunity to:

  • Design and deploy new analytics techniques, algorithms and frameworks for assisting users to query, analyse and derive insights from multimodal knowledge graphs;
  • Apply natural language processing, deep learning language models, data mining and dialog-based interaction techniques to user support systems for deriving insights from multimodal knowledge graphs;
  • Design of appropriate research methodology, evaluation and validation criteria for the proposed ideas and models;
  • Enhance their reputation through publishing in top-quality journals and conferences in collaboration with team members;
  • Nationally and internationally present and represent the groundbreaking research carried out by their and the research team;
  • Contribute to short-term, focused industry projects within ADAPT.

On completion of the PhD program the candidate

  • Will have demonstrated understanding of the problems related to multimodal knowledge graph analysis in general and user-driven analysis support in particular, and have mastered  the skills and methods of empirical research in this emerging field;
  • Will have demonstrated capabilities of defining, designing and implementing appropriate research methodologies with academic integrity and made substantial contribution that extends the knowledge in the field;
  • Be able to communicate concepts and research outputs with their peers and the research community at large and with people outside the field. 

Informal Inquiries can be sent to Dr Rob Brennan (rob.brennan@adaptcentre.ie) or Prof Gareth Jones (gareth.jones@adaptcentre.ie)

Minimum qualifications:

Preferred qualifications:

  • MSc or equivalent in computer science or an aligned field

Preferred Skills:

  • Strong analytical skills and problem-solving skills;
  • Practical knowledge of graph databases, data governance metadata, natural language processing tools such as BERT, and data science tools and techniques; 
  • Experience doing  research in any topic;
  • Academic publication track record; 
  • Experience working on collaborative research with industry or other stakeholders; 
  • Excellent written and verbal communication skills.

 

Application Process

Cover Letter

    • A personal letter of motivation, indicating why you wish to conduct this research project offered by ADAPT, and why you expect that you will be able to complete the research successfully for example ; (500 words maximum)

Detailed CV

    • Detailed curriculum vitae, including – if applicable – evidence of strong analytical skills; details of your final year undergraduate or MSc project; project code repositories; practical knowledge of knowledge graphs, natural language processing, data science; academic publication track record; experience working on collaborative research with industry or other stakeholders; excellent written and verbal communication skills; two academic references.

Diversity

ADAPT is committed to achieving better diversity and gender representation at all levels of the organisation, across leadership, academic, operations, research staff and studentship levels. ADAPT is committed to the continued development of employment policies, procedures and practices that promote gender equality. On that basis we encourage and welcome talented people from all backgrounds to join ADAPT.


Apply Now

Other Positions