PhD Researcher on legal natural language processing

Job description

The UGent Center for the Law of Obligations and Property (CVGR) and the Text-to-Knowledge (T2K) team at IDLab Ghent are seeking a highly motivated and talented PhD student to join their ongoing collaboration on legal applications of natural language processing and AI. The T2K team has worked for many years on natural language processing tasks (NLP), especially on advanced information extraction.  Over the last few years, T2K research tracks have widened towards other subfields and application areas of AI, including in the legal domain, in collaboration with the CVGR. The CVGR has a tradition of in-depth research in contract law and property law, with an increasing emphasis in recent years on digital goods and AI.

In this PhD, you will focus on text-based challenges in the legal domain. A key topic of interest is semantic similarity for legal applications, whereby, for example, two cases may be very similar legally speaking, while being described in apparently very different ways. To this end, a legal language model will be created, by continued pre-training starting from a powerful multi-lingual open-source language model, to be subsequently finetuned for downstream tasks such as legal case similarity in Dutch and French. Applications such as dense retrieval for semantic search of related cases will be investigated.

Throughout the Ph.D., the link with legal professionals will remain important, in order to focus on relevant tasks and with attention to important boundary conditions in legal practice (such as privacy, and different notions of explainability).

Your main tasks will include:

• Reviewing literature on recent language model training and finetuning techniques.
• Preparing considerable online legal data for self-supervised training and creating a benchmark for legal text similarity fine-tuning and evaluation.
• Designing proper training strategies for several text-based tasks, including semantic search, to support legal professionals.
• 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.

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.

The selected candidate will be offered a 4-year employment, with an intermediate evaluation after the first year (1+3 years). The salary is competitive and will be determined by the standardized/fixed university salary scales. In addition, staff members enjoy additional benefits, e.g., a broad range of training and educational opportunities, 36 days of vacation leave, bicycle allowance, and more.

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, i.e., a few months after application) 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 deep learning (with focus on NLP) and are interested in advancing the state-of-the-art for the legal domain in particular.  Hands-on experience in deep learning frameworks such as PyTorch or Tensorflow is a plus.
• You have excellent computer science skills (python, git, linux, etc.)
• 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 and/or French is an important asset, for the collaboration with Belgian legal professionals.

How to apply

Send your application by email to prof. Thomas Demeester and prof. Joke Baeck, with the subject ‘Application PhD (legal NLP)’.

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).

Application deadline: June 30, 2024. 

Start of the Ph.D. research: as soon as September 2024 (or soon after).