Analysis on word embedding and classifier models in legal analytics.

Legal Analytics is a blooming field of research that draws attraction from various fields such as computational linguistics, natural language processing, machine learning, and data science. Improvement in text analytics has paved the way to a great level in eCommerce, banking, medical and legal sectors after the incoming of deep learning models. The large quantity of digital information in the legal domain and the challenges faced has made this an important area of legal research. Historically, judges and other legal personnel have frequently been required to manually review legal documents to acquire an inclusive judgment justification. This practice is highly challenging also laborious and time-consuming. Most of the existing works predict the legal outcomes based on case facts, but predicting judgment solely on Casefact gives low efficiency. Automation in judgment prediction systems is at the budding stage. Choosing the appropriate word embedding technique in language modeling, Classifier model and loss functions pave way for better results. Selecting the appropriate learning algorithm for text classification on real-time problems is a great challenge as legal documents are lengthy and unstructured. This paper emphasizes the limitations and important aspects of different components of NLP such as tokenization, word embeddings, and classifiers which makes the computer interpret and extract maximum contextual information from documents to provide the best performance for assisting litigants for verdict prediction of countries that use common law system. It also reviews different ideas applicable to legal case facts in a broad manner. [ABSTRACT FROM AUTHOR]