PhD Researcher on multimodal & knowledge-grounded dialogue systems

Job description

Ghent University is a world of its own. Employing more than 15,000 people, it is actively involved in education and research, management and administration, as well as technical and social service provision on a daily basis. It is one of the largest, most exciting employers in the area and offers great career opportunities.

 With its 11 faculties and more than 85 departments offering state-of-the-art study programmes grounded in research in a wide range of academic fields, Ghent University is a logical choice for its staff and students.

The IDLab Ghent research group seeks a highly motivated and talented PhD student to join the Text-to-Knowledge (T2K) team. The T2K team has worked for many years on natural language processing tasks (NLP), initially mostly on advanced information extraction, but recently also covering other topics, such as conversational agents.

In this PhD you will focus on designing new conversational AI models, based on recent foundation models. The key research question is how these state-of-the-art language models (including multi-modal versions) can be leveraged and adapted to create an AI-powered voicebot in a recruiting context. Key challenges are to achieve (1) controlled adaptation of the question sequence in the conversation; (2) personalization of dialog flow as well as language; and (3) improving engagement to ultimately limit drop-out of potential candidates. As an underlying building block to address (1) and (2), it is crucial to be able to incorporate external knowledge, in terms of domain knowledge (e.g., specific vocabulary, ontologies of skill sets and/or job titles), and conversation-specific information (e.g., on the interviewee, the organization, a predefined conversation structure). A second aspect, pertaining to both (2) and (3), is to control the bot’s language generation for (cultural/gender) bias, sentiment, etc.

The PhD will be carried out in collaborative projects with other Flemish universities and industry stakeholders. As part of the IDLab text-to-knowledge team (T2K), you will benefit from input/feedback from other PhD students working on related topics.

Your main tasks will include:

•    Studying state-of-the-art techniques and benchmarks in the domain of (multi-modal) conversation modeling, both from the NLP and from human-machine communication perspective.
•    Design, implement, and train new models for conversational AI, with focus on the text modality, but including other modalities as well.
•    Collaborate towards a proof-of-concept implementation of the created models for tests with human participants on a real-world use case. 
•    Writing high quality publications, targeting top journals and international conferences.

In addition to your primary research responsibilities, you will actively contribute to the educational mission of our institution by providing (limited) support for courses in the area of AI, such as Natural Language Processing. In addition, you can take on a mentoring role by supervising master theses related to the subject of this PhD.

Job offer

We offer the opportunity to do this research in an international and stimulating environment. Ghent University consistently ranks among the best 100 universities in the world. Located in the heart of Europe,  Ghent is a beautiful and welcoming city  with plenty of cultural and leisure activities.

We offer a full-time position as a doctoral fellow, consisting of an initial period of 12 months, which, conditional on a positive evaluation, will be extended to a total maximum of 48 months.

Your contract will start on 1/1/25 at the earliest.

The fellowship amount is 100% of the net salary of an AAP member with the same family situation. The individual fellowship amount is determined by the Department of Personnel and Organization based on family status and seniority. A grant that meets the conditions and criteria of the regulations for doctoral fellowships is considered free of personal income tax. Click here for more information about our salary scales.

All Ghent University staff members enjoy several benefits, such as a wide range of training and education opportunities, 36 days of holiday leave (on an annual basis for a full-time job) supplemented by annual fixed bridge days, bicycle allowance, and eco vouchers. Click here for a complete overview of all the staff benefits (in Dutch).

Job profile

We are looking for a highly creative and motivated PhD student with the following qualifications and skills:

•    You have (or will obtain before the starting date) a (European) master's degree in computer science, Mathematics, Artificial Intelligence, or equivalent, with excellent (‘honors’-level) grades. Your degree must be equivalent to 5 years of studies (bachelor + master) in the European Union.
•    You have a strong background in machine learning, including Natural Language Processing.  
•    You have excellent coding skills in Python; hands-on experience in deep learning frameworks such as PyTorch or Tensorflow is a plus
•    You have strong analytical skills to interpret the obtained research results.
•    You are a team player and have strong communication skills.
•    Your English is fluent (C1 CEFR level) both speaking and writing. Knowledge of Dutch is an important asset, for the practical use case collaboration.

How to apply

Send your application by email to prof. Chris Develder and prof. Thomas Demeester, with the subject ‘Application: PhD at T2K (ConvAI)’.

Applications should include:

•    A motivation letter (highlighting why you believe you are a suitable candidate for the position & why you want this position).
•    An academic/professional resume.
•    Transcripts of study results.
•    At least two reference contacts.
•    A short overview describing your earlier research or technical work (e.g., scientific papers, master thesis, report on project work, etc.). Note: This may deviate from the topic of the advertised position.

After a first screening, selected candidates will be invited for an interview (in person or remotely via MS Teams).
Start of the Ph.D. research: January 2025 or later

More info on:
http://t2k.idlab.ugent.be/ 
http://www.lonelyplanet.com/belgium/flanders/ghent