Automatic Catchphrase Identification from Legal Court Case Documents
Arpan Mandal, Kripabandhu Ghosh, Arindam Pal, Saptarshi Ghosh · 2017
Automatically identifying catchphrases from legal court case documents is an important problem in Legal Information Retrieval, which has not been extensively studied. In this work, we propose an unsupervised approach for extraction and ranking of catchphrases from court case documents, by focusing on noun phrases. Using a dataset of gold standard catchphrases created by legal experts from real-life court documents, we compare the proposed approach with several unsupervised and supervised baselines. We show that the proposed methodology achieves statistically significantly better performance compared to all the baselines.