JNLP Team: Deep Learning Approaches for Legal Processing Tasks in COLIEE 2021
This work addresses the problem of processing complex legal texts for researchers and practitioners in legal AI, but it is incremental as it builds on existing deep learning techniques without introducing major innovations.
The paper tackled the challenge of automatic legal document processing by applying deep learning methods to tasks in the COLIEE 2021 competition, reporting experimental results that highlight both the difficulties and potentials of these approaches without specifying concrete numbers.
COLIEE is an annual competition in automatic computerized legal text processing. Automatic legal document processing is an ambitious goal, and the structure and semantics of the law are often far more complex than everyday language. In this article, we survey and report our methods and experimental results in using deep learning in legal document processing. The results show the difficulties as well as potentials in this family of approaches.