Graded Grammaticality: a Computational Framework

by Prost, Jean-Philippe
State: New
VAT included - FREE Shipping
Prost, Jean-Philippe Graded Grammaticality: a Computational Framework
Prost, Jean-Philippe - Graded Grammaticality: a Computational Framework

Do you like this product? Spread the word!

$104.79 incl. VAT
Only 1 items available Only 1 items available
Delivery: between Thursday, December 16, 2021 and Monday, December 20, 2021
Sales & Shipping: Dodax


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.


Prost, Jean-Philippe

Further information

Biography Artist:
Jean-Philippe Prost, Ph.D.: Studied Computer Science jointly at Macquarie University, Sydney, Australia, and Aix-Marseille Université, France. Researcher in Computational Linguistics at Université d''Orléans, France.
Number of Pages:
Media Type:
LAP Lambert Academic Publishing

Master Data

Product Type:
Paperback book
Package Dimensions:
0.22 x 0.15 x 0.014 m; 0.422 kg
We use cookies on our website to make our services more efficient and more user-friendly. Therefore please select "Accept cookies"! Please read our Privacy Policy for further information.