2019 · 25 citations · 9 references
ComputingJurisprudenceComparative JurisprudenceNatural Language ProcessingPhilosophy Of LawText MiningText Similarity AnalysisWord EmbeddingsDocument SimilarityDocument Similarity AssessmentDocument Similarity MeasuresLegal CorporaLegal Information RetrievalSimilarity Analysis
With the increasing demand for computer-assisted wisdom in justice, deep learning has gradually become an effective means of helping intelligent justice. The similarity analysis of law documents is the basis of intelligent justice, while law documents based on several types of cases are quite different in terms of format and length, which causes trouble in analyzing similarities. For that we propose a more specific approach to dealing with law documents, combining Word2vec with legal documents corpus. To measure the efficiency of the proposed method, we designed two sets of controls. The experimental results show that the Word2vec model can improve the accuracy by 0.20 compared with the bag of words (BOW) model, and the equipped law documents corpus can increase by 0.05-0.10 based on the Word2vec model. Thus, the combination of Word2vec and the law documents corpus is more compatible with the simple and efficient application of similarity analysis of law documents.
9
Efficient Estimation of Word Representations in Vector Space
Tomáš Mikolov, Kai Chen, Greg S. Corrado et al. · arXiv (Cornell University) · 2013 · 11.7K citations · Full text
Learning Word Vectors for Sentiment Analysis
Andrew L. Maas, Raymond E. Daly, Peter T. Pham et al. · 2011 · 3.3K citations
A neural probabilistic language model
BengioYoshua, DucharmeRéjean, VincentPascal et al. · Journal of Machine Learning Research · 2003 · 2.7K citations