Description: Language resources and computational models are becoming increasingly important for the study of language variation. A main challenge of this interdisciplinary field is that linguistics researchers may not be familiar with these helpful computational tools and many NLP researchers are often not familiar with language variation phenomena. This essential reference introduces researchers to the necessary computational models for processing similar languages, varieties, and dialects. In this book, leading experts tackle the inherent challenges of the field by balancing a thorough discussion of the theoretical background with a meaningful overview of state-of-the-art language technology. The book can be used in a graduate course, or as a supplementary text for courses on language variation, dialectology, and sociolinguistics or on computational linguistics and NLP. Part 1 covers the linguistic fundamentals of the field such as the question of status and language variation. Part 2 discusses data collection and pre-processing methods. Finally, Part 3 presents NLP applications such as speech processing, machine translation, and language-specific issues in Arabic and Chinese.
Brief description: Dr. Marcos Zampieri is an assistant professor at the Rochester Institute of Technology, where he teaches courses in linguistics and natural language processing. He received his PhD for Saarland University in Germany with a thesis on computational models applied to pluricentric languages. Dr. Zampieri is one of the organizers of the well-established VarDial workshop series on NLP for Similar Languages, Varieties, and Dialects. His research deals with the application of computational models to large collections of texts. He has worked on a variety of topics including language acquisition and variation, (machine) translation and post-editing, and social media mining.
Review Quotes: 'Variation is a key aspect of human language, and yet it has been too often overlooked in computational linguistics. The book edited by Marcos Zampieri and Preslav Nakov is an important step towards filling this gap with top-level contributions that offer a new alliance between natural language processing and linguistic theory to understand this complex phenomenon and its impact on applications.' Alessandro Lenci, University of Pisa