Repozytorium publikacji - Politechnika Gdańska

We present a system for retrieving the most relevant legal opinions to a given legal case or question. To this end, we checked several state-of-the-art neural language models. As a training and testing data, we use tens of thousands of legal cases as question-opinion pairs. Text data has been subjected to advanced pre-processing adapted to the specifics of the legal domain. We empirically chose the BERT-based HerBERT model to perform the best in the considered scenario.

Autorzy

• Maciej Osowski,
• Katarzyna Lorenc,
• Paweł Drozda,
• Rafał Scherer,
• Konrad Szałapak,
• Kajetan Komar-Komarowski,
• dr hab. inż. Julian Szymański link otwiera się w nowej karcie ,
• dr inż. Andrzej Sobecki link otwiera się w nowej karcie