Semantic NLP Technologies in Information Retrieval Systems for Legal Research

Companies involved in providing legal research services to lawyers, such as LexisNexis or Westlaw, have rapidly incorporated natural language processing (NLP) into their database systems to deal with the massive amounts of legal texts contained within them. These NLP techniques, which perform analysis on natural language texts by taking advantage of methods developed in the fields of computational linguistics and artificial intelligence, have potential applications ranging from text summarization all the way to the prediction of court judgments. However, a potential concern with the use of this technology is that professionals will come to depend on systems, over which they have little control or understanding, as a source of knowledge. While recent strides in AI and deep learning have led to increased effectiveness in NLP techniques, the decision-making processes of these algorithms have progressively become less intuitive for humans to understand. Concerns about the interpretability of patented legal services such as LexisNexis are more pertinent than ever. The following survey conducted for current NLP techniques shows that one potential avenue to make algorithms in NLP more explainable is to incorporate symbol-based methods that take advantage of knowledge models generated for specific domains. An example of this can be seen in NLP techniques developed to facilitate the retrieval of inventive information from patent applications.