Natural Language Processing
Another technology used in LegalTech is natural language processing (NLP). It is the application of linguistics, statistics, and computer science to problems related to spoken or written language.
NLP systems are able to convert samples of human language into machine readable format, and to convert information from computer databases into readable human language (cf. Ela Kumar, Natural Language Processing, 2011, 1). NLP is at work if someone asks Siri on his IPhone. NLP is challenging because computers traditionally require a programming language that is precise, unambiguous and highly structured. Human speech, however, is often ambiguous and the linguistic structure can depend on many complex variables, including slang, regional dialects and social context.Many NLP applications today use “shallow NLP” or “statistical NLP” techniques. These applications do not “understand” the meaning of a word, phrase or sentence. They have just memorized certain words, patterns, or statistical associations between words. For a NLP tool to show “intelligent” behaviour (for example, interpreting a legal contract), the tool would need to understand legal concepts. In addition, it would need to be able to reason or combine information from different sources. NLP researchers are working in two areas—semantics and pragmatics—that may eventually enable computers to “understand” written text or spoken language. NLP may lead to applications that can acquire knowledge on their own, or are able to reason in an intelligent manner. If this occurs, lawyers could potentially use NLP to build applications that are capable of understanding contracts and cases, researching legal topics on their own and making predictions about potential outcomes.
To sum up, LegalTech applications might use AI techniques, such as machine learning or NLP, to replicate intelligent behaviours. However, other tools or “normal” software solutions might be deployed as well to improve the way legal work and supportive activities are carried out.
4