Text Mining and Retrieval Leiden (TMRL) is the research group of Suzan Verberne at Leiden University. The group was founded in 2017 as one of the Special Interest Groups (SIGs) of the Data Science research programme and is now part of the Data Science cluster at the Leiden Institute of Advanced Computer Science (LIACS).
Since 2017, the group has led to a series of successful PhD graduates, some of which were firmly anchored in interdisciplinary collaboration with impact in application domains (health, archaeology, and law).
The current research focus of the group is on domain-specific Natural Language Processing (NLP) and Information Retrieval (IR). We develop novel methods for representation learning, ranking, and information extraction on a large diversity of textual data: archaeological reports, patents, scientific and legal publications, health records, newspaper texts, user-generated content in online patient communities (discussion forums), and posts on social media. In addition, we engage in more fundamental research addressing the linguistic underpinnings Large Language Models (LLMs) and challenges related to bias and transparency of these models and their applications.
Social values of our group are: diversity (in background, working style, and personal interests) & inclusivity; teamwork (a PhD project can feel as a lonely job, but not if you have peers that support you); and work-life balance (yes, we take time off during weekends and vacations).
You can follow us on Twitter and GitHub.