Towards De-identification of Legal Texts
This addresses privacy concerns in legal document sharing, but the results are incremental as they highlight domain-specific adaptation needs.
The paper tackled the problem of de-identifying legal texts to hide names in lawsuits, but found that existing NLP tools performed poorly, with 84% of documents having at least one name not covered by named entity recognition.
In many countries, personal information that can be published or shared between organizations is regulated and, therefore, documents must undergo a process of de-identification to eliminate or obfuscate confidential data. Our work focuses on the de-identification of legal texts, where the goal is to hide the names of the actors involved in a lawsuit without losing the sense of the story. We present a first evaluation on our corpus of NLP tools in tasks such as segmentation, tokenization and recognition of named entities, and we analyze several evaluation measures for our de-identification task. Results are meager: 84% of the documents have at least one name not covered by NER tools, something that might lead to the re-identification of involved names. We conclude that tools must be strongly adapted for processing texts of this particular domain.