It was a lot of fun presenting my very first (long) paper at ACL2022 in Dublin! ๐Ÿ‡ฎ๐Ÿ‡ช๐Ÿ‡ฎ๐Ÿ‡ช๐Ÿ‡ฎ๐Ÿ‡ช

There, I talked about a brand new dataset for legal information retrieval. It consists of 1100+ questions labeled with relevant legislation from a corpus of 22600+ law articles.

With questions such as โ€œWhat do I risk if I violate professional confidentiality?โ€ or โ€œCan I miss work to visit the doctor?โ€, the dataset allows to develop retrieval models that can help bridge the gap between people and the law.

โ†’ Paper:

โ†’ Dataset: