Solving linguistic problems not infrequently reduces to carrying out tasks that are computationally complex and therefore requires automation. In such situations, the difference between having and not having computational tools to handle the tasks is not a matter of economy of time and effort, but may amount to the difference between finding and not finding a solution at all. The book is an introduction to machine-aided linguistic discovery, a novel research area, arguing for the fruitfulness of the computational approach by presenting a basic conceptual apparatus and several intelligent discovery programmes. One of the systems models the fundamental Saussurian notion of system, and thus, for the first time, after almost a century after the introduction of this concept and structuralism in general, linguists are capable to handle adequately this recurring computationally complex task. Another system models the problem of searching for Greenbergian language universals and is capable of stating its discoveries in an intelligible form, viz. a comprehensive English language text, thus constituting the first computer program to generate a whole scientific article.
Yet another system detects potential inconsistencies in genetic language classifications. The programmes are applied with noteworthy results to substantial problems from diverse linguistic disciplines such as structural semantics, phonology, typology and historical linguistics.
Vladimir Pericliev is Senior Researcher at the Institute of Mathematics & Informatics, Bulgarian Academy of Sciences, with over 60 publications in general and computational linguistics, Artificial Intelligence and philosophy of science.