@inproceedings{soh-etal-2019-legal,
    title = "Legal Area Classification: A Comparative Study of Text Classifiers on {S}ingapore {S}upreme {C}ourt Judgments",
    author = "Soh, Jerrold  and
      Lim, How Khang  and
      Chai, Ian Ernst",
    editor = "Aletras, Nikolaos  and
      Ash, Elliott  and
      Barrett, Leslie  and
      Chen, Daniel  and
      Meyers, Adam  and
      Preotiuc-Pietro, Daniel  and
      Rosenberg, David  and
      Stent, Amanda",
    booktitle = "Proceedings of the Natural Legal Language Processing Workshop 2019",
    month = jun,
    year = "2019",
    address = "Minneapolis, Minnesota",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/iwcs-25-ingestion/W19-2208/",
    doi = "10.18653/v1/W19-2208",
    pages = "67--77",
    abstract = "This paper conducts a comparative study on the performance of various machine learning approaches for classifying judgments into legal areas. Using a novel dataset of 6,227 Singapore Supreme Court judgments, we investigate how state-of-the-art NLP methods compare against traditional statistical models when applied to a legal corpus that comprised few but lengthy documents. All approaches tested, including topic model, word embedding, and language model-based classifiers, performed well with as little as a few hundred judgments. However, more work needs to be done to optimize state-of-the-art methods for the legal domain."
}