Multi-granular Legal Topic Classification on Greek Legislation
This work addresses the lack of NLP resources for Greek legal text classification, which is an incremental contribution to a domain-specific problem.
The paper tackles the problem of classifying legal texts in Greek by introducing a novel dataset of over 47,000 official Greek legislation resources and evaluating various methods, showing that recurrent architectures with domain-specific embeddings offer improved performance while being competitive with transformer models.
In this work, we study the task of classifying legal texts written in the Greek language. We introduce and make publicly available a novel dataset based on Greek legislation, consisting of more than 47 thousand official, categorized Greek legislation resources. We experiment with this dataset and evaluate a battery of advanced methods and classifiers, ranging from traditional machine learning and RNN-based methods to state-of-the-art Transformer-based methods. We show that recurrent architectures with domain-specific word embeddings offer improved overall performance while being competitive even to transformer-based models. Finally, we show that cutting-edge multilingual and monolingual transformer-based models brawl on the top of the classifiers' ranking, making us question the necessity of training monolingual transfer learning models as a rule of thumb. To the best of our knowledge, this is the first time the task of Greek legal text classification is considered in an open research project, while also Greek is a language with very limited NLP resources in general.