Imperial College London Featured PhD Programmes
Xi’an Jiaotong-Liverpool University Featured PhD Programmes
University of Hong Kong Featured PhD Programmes

NLG4XAI: Natural Language Generation for the iSee Explainable AI Platform Robert Gordon University


   School of Computing

This project is no longer listed on FindAPhD.com and may not be available.

Click here to search FindAPhD.com for PhD studentship opportunities
  Prof N Wiratunga, Dr Ikechukwu Nkisi-Orji  No more applications being accepted  Funded PhD Project (Students Worldwide)

About the Project

Applications are sought for a fully funded Research Studentship (PhD) to carry out research at Robert Gordon University, Aberdeen, United Kingdom. The successful candidate will be working within the AI and Reasoning research group led by Professor Nirmalie Wiratunga and under the direct supervision of Dr Ikechukwu Nkisi-Orji.

Duration and Funding

The duration of the project will be up to 36 months, commencing in 2021. The studentship covers both tuition fees (at UK or International level) and a tax-free stipend (living allowance) of £15,000 per annum.

The successful candidate will be required to relocate to Aberdeen as soon as possible to study, although studies may start remotely initially; this is an essential requirement of the studentship and is not open to negotiation.

Proposed Research

A right to obtain an explanation of the decision reached by a machine learning (ML) model is now an EU regulation. Different stakeholders (e.g., managers, developers, auditors, etc.) may have different background knowledge, competencies and goals, thus requiring different kinds of interpretations and explanations. Fortunately, there is a growing armoury of ways of interpreting black-box ML models and explaining their predictions, recommendations and diagnoses. We will refer to these collectively as explanation strategies. As these explanation strategies mature, practitioners will gain experience that helps them know which strategies to deploy in different circumstances.

The proposed research aims to investigate the role of natural language generation (NLG) in the presentation of explanation strategies. For instance, in response to an end-user’s explanation need the system could provide alternative forms of explanations, such as those from salience visualisations; or relevance feature weights or counterfactual examples; or indeed a combination of these explanation strategies.

However, what, when, and how to present these explanations plays an important role towards supporting end-users complete their tasks as well as achieving satisfaction and trust in the black-box model. A related question is how to use conversational AI to understand and tease out end-users explanation needs.

Generating natural language summaries of explanation strategies that are contextually relevant remains a challenge for explainable AI.

More specifically, topics such as natural language understanding, natural language generation and case-based reasoning will be explored to improve the quality of user interaction and natural language explanations generated within the multi-strategy iSee explanation platform.

During the research study, the student will work with the iSee EU consortium (https://isee4xai.com/) and leverage the existing expertise and collaboration between the academic and industrial partners in this research area. The successful candidate will have the opportunity to work with iSee’s usecase partners (e.g., BT France, jiva.ai, Bosch) as well as iSee’s academic partners.

Key Skills

Applicants should have a very good BSc (Honours) (First or Upper Second class) degree or a Master degree (with Distinction or Merit) in Computing Science or related discipline.

Essential Knowledge and Experience:

  • Strong programming skill in Python/Java or similar languages.
  • Knowledge of machine learning packages (Tensorflow/Keras, NLTK or similar).
  • Experience with deep learning, natural language processing and information extraction.
  • Good analytical skills - knowledge of foundations of computer science, ability to think independently.
  • Strong oral and written communication skills, in both plain English and academic languages, for publication in relevant journals and presentation at conferences.

Desirable requirements

  • Knowledge of explainable AI and research related to natural language generation.
  • Knowledge of ontological knowledge resources.
  • Mixed-method evaluation including knowledge of statistical tools (R/MatLab or similar).
  • Experience with co-creation and end-user facing activities.

Applicants should have good personal and communication skills, strong professionalism and integrity, and be capable of working on their own initiative.

Enquiries

Enquiries can be submitted through the findaphd.com portal or emailed to [Email Address Removed] and will be forwarded to Professor Nirmalie Wiratunga and Dr Ikechukwu Nkisi-Orji if technical in nature.

Applications

Applications should be submitted through the findaphd.com portal or be emailed direct to [Email Address Removed] by midnight, Tuesday, 31 August 2021. The application should consist of:

  • A covering letter or personal statement of interest
  • CV
  • IELTS (or equivalent) certificate
  • Two references - at least one of which should be academic or professional

Further information such as passport details or transcripts may be requested during the short-listing stage. Interviews (which may include a short practical test) are expected to take place September 2021.

For more information regarding the University's English language requirements please visit: https://www.rgu.ac.uk/study/international-students/english-language-requirements


Funding Notes

Studentship is open to ALL students who meet the key requirements - UK or worldwide - please note the requirement to re-locate to Aberdeen, UK.
The duration of the project will be up to 36 months, commencing in 2021. The studentship covers both tuition fees (at UK or International level) and a tax-free stipend (living allowance) of £15,000 per annum.
The successful candidate will be required to relocate to Aberdeen as soon as possible to study, although studies may start remotely initially; this is an essential requirement of the studentship and is not open to negotiation.

References

Two references - at least one of which should be academic or professional
Search Suggestions
Search suggestions

Based on your current searches we recommend the following search filters.