Parsing Efficiency is crucial when building practical natural language systems. 'Ibis is especially the case for interactive systems such as natural language database access, interfaces to expert systems and interactive machine translation. Despite its importance, parsing efficiency has received little attention in the area of natural language processing. In the areas of compiler design and theoretical computer science, on the other hand, parsing algorithms 3 have been evaluated primarily in terms of the theoretical worst case analysis (e.g. lXn», and very few practical comparisons have been made. This book introduces a context-free parsing algorithm that parses natural language more efficiently than any other existing parsing algorithms in practice. Its feasibility for use in practical systems is being proven in its application to Japanese language interface at Carnegie Group Inc., and to the continuous speech recognition project at Carnegie-Mellon University. This work was done while I was pursuing a Ph.D degree at Carnegie-Mellon University. My advisers, Herb Simon and Jaime Carbonell, deserve many thanks for their unfailing support, advice and encouragement during my graduate studies. I would like to thank Phil Hayes and Ralph Grishman for their helpful comments and criticism that in many ways improved the quality of this book. I wish also to thank Steven Brooks for insightful comments on theoretical aspects of the book (chapter 4, appendices A, B and C), and Rich Thomason for improving the linguistic part of tile book (the very beginning of section 1.1).

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.

The Generalized LR parsing algorithm (some call it "Tomita's algorithm") was originally developed in 1985 as a part of my Ph.D thesis at Carnegie Mellon University. When I was a graduate student at CMU, I tried to build a couple of natural language systems based on existing parsing methods. Their parsing speed, however, always bothered me. I sometimes wondered whether it was ever possible to build a natural language parser that could parse reasonably long sentences in a reasonable time without help from large mainframe machines. At the same time, I was always amazed by the speed of programming language compilers, because they can parse very long sentences (i.e., programs) very quickly even on workstations. There are two reasons. First, programming languages are considerably simpler than natural languages. And secondly, they have very efficient parsing methods, most notably LR. The LR parsing algorithm first precompiles a grammar into an LR parsing table, and at the actual parsing time, it performs shift-reduce parsing guided deterministically by the parsing table. So, the key to the LR efficiency is the grammar precompilation; something that had never been tried for natural languages in 1985. Of course, there was a good reason why LR had never been applied for natural languages; it was simply impossible. If your context-free grammar is sufficiently more complex than programming languages, its LR parsing table will have multiple actions, and deterministic parsing will be no longer possible.

Parsing, the syntactic analysis of language, has been studied extensively in computer science and computational linguistics. Computer programs and natural languages share an underlying theory of formal languages and require efficient parsing algorithms. This introduction reviews the theory of parsing from a novel perspective. It provides a formalism to capture the essential traits of a parser that abstracts from the fine detail and allows a uniform description and comparison of a variety of parsers, including Earley, Tomita, LR, Left-Corner, and Head-Corner parsers. The emphasis is on context-free phrase structure grammar and how these parsers can be extended to unification formalisms. The book combines mathematical rigor with high readability and is suitable as a graduate course text.

Memory-based language processing - a machine learning and problem solving method for language technology - is based on the idea that the direct reuse of examples using analogical reasoning is more suited for solving language processing problems than the application of rules extracted from those examples. This book discusses the theory and practice of memory-based language processing, showing its comparative strengths over alternative methods of language modelling. Language is complex, with few generalizations, many sub-regularities and exceptions, and the advantage of memory-based language processing is that it does not abstract away from this valuable low-frequency information. By applying the model to a range of benchmark problems, the authors show that for linguistic areas ranging from phonology to semantics, it produces excellent results. They also describe TiMBL, a software package for memory-based language processing. The first comprehensive overview of the approach, this book will be invaluable for computational linguists, psycholinguists and language engineers.

TheInternationalConferenceTSD 2005,the8theventin theseriesonText,Speech,and Dialogue, which originated in 1998, presented state-of-the-art technology and recent achievements in the ?eld of natural language processing. It declared its intent to be an interdisciplinary forum, intertwining research in speech and language processing with its applications in everyday practice. We feel that the mixture of different approaches and applications offered a great opportunity to get acquainted with the current act- ities in all aspects of language communication and to witness the amazing vitality of researchers from developing countries too. The ?nancial support of the ISCA (Inter- tional Speech Communication Association) enabled the wide attendance of researchers from all active regions of the world. Thisyear’sconferencewaspartiallyorientedtowardsmulti-modalhuman-computer interaction (HCI), which can be seen as the most attractive topic of HCI at the present time. In this way, we are involved in a rich complex of communicative activity, facial expressions, hand gestures, direction of gaze, to name but the most obvious ones. The interpretationof each user utterancedependson the context,prosody,facial expressions (e. g. brows raised, brows and gaze both raised) and gestures. Hearers have to adapt to the speaker (e. g. maintainingthe theme of the conversation,smiling etc. ). Research into the interaction of these channels is however limited, often focusing on the interaction between a pair of channels. Six signi?cant scienti?c results achieved in this area in the USA, Japan, Switzerland, Germany, The Netherlands, and the Czech Republic were presented by keynote speakers in special plenary sessions. Further, approx.

The Generalized LR parsing algorithm (some call it "Tomita's algorithm") was originally developed in 1985 as a part of my Ph.D thesis at Carnegie Mellon University. When I was a graduate student at CMU, I tried to build a couple of natural language systems based on existing parsing methods. Their parsing speed, however, always bothered me. I sometimes wondered whether it was ever possible to build a natural language parser that could parse reasonably long sentences in a reasonable time without help from large mainframe machines. At the same time, I was always amazed by the speed of programming language compilers, because they can parse very long sentences (i.e., programs) very quickly even on workstations. There are two reasons. First, programming languages are considerably simpler than natural languages. And secondly, they have very efficient parsing methods, most notably LR. The LR parsing algorithm first precompiles a grammar into an LR parsing table, and at the actual parsing time, it performs shift-reduce parsing guided deterministically by the parsing table. So, the key to the LR efficiency is the grammar precompilation; something that had never been tried for natural languages in 1985. Of course, there was a good reason why LR had never been applied for natural languages; it was simply impossible. If your context-free grammar is sufficiently more complex than programming languages, its LR parsing table will have multiple actions, and deterministic parsing will be no longer possible.