Named entity recommendation on Brazilian Legal Text (LeNER-BR)
Example project
This project show-cases the OpenNLP named entity recommender on a sample of texts from LeNER-BR, a dataset for named entity recognition in Brazilian Legal Text composed of legislation and legal decision texts. As named entity categories we have Person, Organization, Time, Location, Legislation and Legal Decisions.
The project contains five annotated documents. From the first document (AC10024133855890001.txt
), all annotations were stripped. We have configured an OpenNLP Named Entity Recognizer recommender as well as a String-based recommender which both learn on the 5 annotated documents and provides recommendations on the unannotated document. When you open the first document on the annotation page, the learning of the recommender is triggered. It may take a moment until the recommendations become actually visible. Try re-loading the page after a minute - then the recommendations should show up.
References
- Pedro Henrique Luz de Araujo, Teófilo E. de Campos, Renato R. R. de Oliveira, Matheus Stauffer, Samuel Couto, Paulo Bermejo. LeNER-Br: A Dataset for Named Entity Recognition in Brazilian Legal Text. Computational Processing of the Portuguese Language, Springer International Publishing. [PDF (pre-print)] [Publisher] [BIB]
- LeNER-Br: a Dataset for Named Entity Recognition in Brazilian