Dependency-based methods for syntactic parsing have become increasingly popular in natural language processing in recent years. This book gives a thorough introduction to the methods that are most widely used today. After an introduction to dependency grammar and dependency parsing, followed by a formal characterization of the dependency parsing problem, the book surveys the three major classes of parsing models that are in current use: transition-based, graph-based, and grammar-based models. It continues with a chapter on evaluation and one on the comparison of different methods, and it closes with a few words on current trends and future prospects of dependency parsing. The book presupposes a knowledge of basic concepts in linguistics and computer science, as well as some knowledge of parsing methods for constituency-based representations. Table of Contents: Introduction / Dependency Parsing / Transition-Based Parsing / Graph-Based Parsing / Grammar-Based Parsing / Evaluation / Comparison / Final Thoughts

Since 2002, FoLLI has awarded an annual prize for outstanding dissertations in the fields of Logic, Language and Information. This book is based on the PhD thesis of Marco Kuhlmann, joint winner of the E.W. Beth dissertation award in 2008. Kuhlmann’s thesis lays new theoretical foundations for the study of non-projective dependency grammars. These grammars are becoming increasingly important for approaches to statistical parsing in computational linguistics that deal with free word order and long-distance dependencies. The author provides new formal tools to define and understand dependency grammars, presents two new dependency language hierarchies with polynomial parsing algorithms, establishes the practical significance of these hierarchies through corpus studies, and links his work to the phrase-structure grammar tradition through an equivalence result with tree-adjoining grammars. The work bridges the gaps between linguistics and theoretical computer science, between theoretical and empirical approaches in computational linguistics, and between previously disconnected strands of formal language research.

The book presents a wide range of recent research results about parsing schemata, introducing formal frameworks and theoretical results while keeping a constant focus on applicability to practical parsing problems. The first part includes a general introduction to the parsing schemata formalism that contains the basic notions needed to understand the rest of the parts. Thus, this compendium can be used as an introduction to natural language parsing, allowing postgraduate students not only to get a solid grasp of the fundamental concepts underlying parsing algorithms, but also an understanding of the latest developments and challenges in the field. Researchers in computational linguistics will find novel results where parsing schemata are applied to current problems that are being actively researched in the computational linguistics community (like dependency parsing, robust parsing, or the treatment of non-projective linguistics phenomena). This book not only explains these results in a more detailed, comprehensive and self-contained way, and highlights the relations between them, but also includes new contributions that have not been presented.

This book presents a comprehensive overview of semi-supervised approaches to dependency parsing. Having become increasingly popular in recent years, one of the main reasons for their success is that they can make use of large unlabeled data together with relatively small labeled data and have shown their advantages in the context of dependency parsing for many languages. Various semi-supervised dependency parsing approaches have been proposed in recent works which utilize different types of information gleaned from unlabeled data. The book offers readers a comprehensive introduction to these approaches, making it ideally suited as a textbook for advanced undergraduate and graduate students and researchers in the fields of syntactic parsing and natural language processing.

This book describes the framework of inductive dependency parsing, a methodology for robust and efficient syntactic analysis of unrestricted natural language text. Coverage includes a theoretical analysis of central models and algorithms, and an empirical evaluation of memory-based dependency parsing using data from Swedish and English. A one-stop reference to dependency-based parsing of natural language, it will interest researchers and system developers in language technology, and is suitable for graduate or advanced undergraduate courses.

In the last decade, AI firmly settled into our industrial society with the expert systems as the representative product. However, almost every one of the systems could cover only a single task domain. In the highly mechanized world of the 21st century, systems will become smart and user friendly enough to cover a wide range of task domains. Systems with much user friendliness must be multilingual because users in different domains usually have different languages. Language is formed in its own culture. Therefore, promotion for cross-cultural scientific interchange will be indispensable for the progress of AI.