Master's Thesis Martina Preis

A Structured Overview of Use Cases for Natural Language Processing in the Legal Domain

The concept of LegalTech has gained increased attention in recent years. In essence, the potential for Natural Language Processing (NLP) techniques to aid in the promotion of the legal sector presents a promising field of research. While a considerable amount of research has been conducted in LegalTech, the focus is mainly application based. At the same time, little work has been performed investigating the use cases of NLP in the legal domain.

The proposed research topic would firstly take the form of a systematic literature review, where the student would perform a rigorous search of relevant LegalTech papers, particularly those from prominent NLP outlets. In the data synthesis and analysis phase, an emphasis should be placed on identifying the legal use cases, which the NLP literature covers. 

The next phase of the thesis would be to supplement the findings of the literature review via the conduction of semi-structured interviews with experts in the field. These interviews will be crucial to tie the knowledge gained from the review to practice.

This study would be an important first step in the context of the NLawP project, which first seeks to perform empirical research into the current state-of-the-art of LegalTech. In conjunction with expert interviews, the literature review findings will be crucial to creating the first project deliverable: a NLawP Tech Map.

Research Questions: 

• RQ1: From a technical perspective, what are the predominant Natural Language Processing techniques being applied in the legal domain, and to what extent are ethical, legal, and social aspects covered?
• RQ2: What are the use cases in which the identified NLP techniques can be utilized?
• RQ3: Together with semi-structured interviews, how can the results of the systematic literature review be synthesized with legal expertise to form the basis of a joint knowledge base?