Named Entity Recognition in the Legal Domain using a Pointer Generator Network
This work provides an incremental improvement for legal professionals and researchers working with noisy legal documents, offering a method to perform NER without gold standard data.
This paper addresses Named Entity Recognition (NER) in the legal domain using noisy text from court case PDFs. The authors reformulate NER as a text-to-text sequence generation task and train a pointer generator network to extract entities, outperforming common NER neural network architectures in long legal documents even with partially complete training data.
Named Entity Recognition (NER) is the task of identifying and classifying named entities in unstructured text. In the legal domain, named entities of interest may include the case parties, judges, names of courts, case numbers, references to laws etc. We study the problem of legal NER with noisy text extracted from PDF files of filed court cases from US courts. The "gold standard" training data for NER systems provide annotation for each token of the text with the corresponding entity or non-entity label. We work with only partially complete training data, which differ from the gold standard NER data in that the exact location of the entities in the text is unknown and the entities may contain typos and/or OCR mistakes. To overcome the challenges of our noisy training data, e.g. text extraction errors and/or typos and unknown label indices, we formulate the NER task as a text-to-text sequence generation task and train a pointer generator network to generate the entities in the document rather than label them. We show that the pointer generator can be effective for NER in the absence of gold standard data and outperforms the common NER neural network architectures in long legal documents.