Artificial Intelligence, Machine & Deep Learning, Natural Language Processing & Understanding, Data Mining, Big Data Analytics
Modeling law search and retrieval as prediction problems has recently emerged as a predominant approach in law intelligence. Focusing on the law article retrieval task, we present a deep learning framework, which is designed for law codes, and specifically to address an extreme classification scenario, which is characterized by a high number of classes, the few-shot learning problem. Furthermore, we provide insights into the explainability and interpretability of our models. We can obtain deep contextualized embeddings which can be interpretated as semantic representations of the textual data. We can use these numerical representations to enrich networks of law articles references.