The grammaticality of a sentence has conventionally been treated in a binary way: either a sentence is grammatical or not. Yet, it is commonly acknowledged that a natural language, in its everyday use, is uttered along various degrees of grammatical acceptability, with utterances being more grammatical than others. A growing body of academic work focuses on studying intermediate levels of acceptability, sometimes referred to as 'gradience'. To date, the bulk of this work has concerned itself with the exploration of human assessments of syntactic gradience. This book explores the possibility to build a robust computational model that accords with these human judgements. A solution is presented to make an optimal use of the linguistic knowledge about a grammatical or non-canonical sentence, and rate that sentence according to grammatical judgements. This book should be of interest to linguists and computer scientists, whether academics or professionals in the Natural Language Processing industry, who are interested in the robust processing of syntactic knowledge about unrestricted language.
