学术文献库

Rules are pervasive in the law. In the context of computer engineering, the translation of legal text to algorithmic form is seemingly direct. In large part, law may be a ripe field for expert systems and machine learning. For engineers, existing law appears formulaic and logically reducible to "if, then" statements. The underlying assumption is that the legal language is both self-referential and universal. Moreover, description is considered distinct from interpretation; that in describing the law, the language is seen as quantitative and objectifiable. Nevertheless, is descriptive formal language purely dissociative? From the logic machine of the 1970s to the modern fervor for artificial intelligence (AI), governance by numbers is making a persuasive return. Could translation be possible? The project follows a fundamentally semantic conundrum: what is the significance of "meaning" in legal language? The project, therefore, tests translation by deconstructing sentences from existing legal judgments to their constituent factors. Definitions are then extracted in accordance with the interpretations of the judges. The intent is to build an expert system predicated on alleged rules of legal reasoning. The authors apply both linguistic modelling and natural language processing technology to parse the legal judgments. The project extends beyond prior research in the area, combining a broadly statistical model of context with the relative precision of syntactic structure. The preliminary hypothesis is that, by analyzing the components of legal language with a variety of techniques, we can begin to translate law to numerical form.