In this book we address robustness issues at the speech recognition and natural language parsing levels, with a focus on feature extraction and noise robust recognition, adaptive systems, language modeling, parsing, and natural language understanding. This book attempts to give a clear overview of the main technologies used in language and speech processing, along with an extensive bibliography to enable topics of interest to be pursued further. It also brings together speech and language technologies often considered separately. Robustness in Language and Speech Technology serves as a valuable reference and although not intended as a formal university textbook, contains some material that can be used for a course at the graduate or undergraduate level.

Corpus-based methods will be found at the heart of many language and speech processing systems. This book provides an in-depth introduction to these technologies through chapters describing basic statistical modeling techniques for language and speech, the use of Hidden Markov Models in continuous speech recognition, the development of dialogue systems, part-of-speech tagging and partial parsing, data-oriented parsing and n-gram language modeling. The book attempts to give both a clear overview of the main technologies used in language and speech processing, along with sufficient mathematics to understand the underlying principles. There is also an extensive bibliography to enable topics of interest to be pursued further. Overall, we believe that the book will give newcomers a solid introduction to the field and it will give existing practitioners a concise review of the principal technologies used in state-of-the-art language and speech processing systems. Corpus-Based Methods in Language and Speech Processing is an initiative of ELSNET, the European Network in Language and Speech. In its activities, ELSNET attaches great importance to the integration of language and speech, both in research and in education. The need for and the potential of this integration are well demonstrated by this publication.

Yorick Wilks is a central figure in the fields of Natural Language Processing and Artificial Intelligence. This book celebrates Wilks s career from the perspective of his peers in original chapters each of which analyses an aspect of his work and links it to current thinking in that area. This volume forms a two-part set together with Words and Intelligence I: Selected Works by Yorick Wilks, by the same editors."

This is the first comprehensive overview of computational approaches to Arabic morphology. The subtitle aims to reflect that widely different computational approaches to the Arabic morphological system have been proposed. The book provides a showcase of the most advanced language technologies applied to one of the most vexing problems in linguistics. It covers knowledge-based and empirical-based approaches.

Many approaches have already been proposed for classification and modeling in the literature. These approaches are usually based on mathematical mod els. Computer systems can easily handle mathematical models even when they are complicated and nonlinear (e.g., neural networks). On the other hand, it is not always easy for human users to intuitively understand mathe matical models even when they are simple and linear. This is because human information processing is based mainly on linguistic knowledge while com puter systems are designed to handle symbolic and numerical information. A large part of our daily communication is based on words. We learn from various media such as books, newspapers, magazines, TV, and the Inter net through words. We also communicate with others through words. While words play a central role in human information processing, linguistic models are not often used in the fields of classification and modeling. If there is no goal other than the maximization of accuracy in classification and model ing, mathematical models may always be preferred to linguistic models. On the other hand, linguistic models may be chosen if emphasis is placed on interpretability."

The lexicon is now a major focus of research in computational linguistics and natural language processing (NLP), as more linguistic theories concentrate on the lexicon and as the acquisition of an adequate vocabulary has become the chief bottleneck in developing practical NLP systems. This collection describes techniques of lexical representation within a unification-based framework and their linguistic application, concentrating on the issue of structuring the lexicon using inheritance and defaults. Topics covered include typed feature structures, default unification, lexical rules, multiple inheritance and non-monotonic reasoning. The contributions describe both theoretical results and implemented languages and systems, including DATR, the Stuttgart TFS and ISSCO's ELU. This book arose out of a workshop on default inheritance in the lexicon organized as a part of the Esprit ACQUILEX project on computational lexicography. Besides the contributed papers mentioned above, it contains a detailed description of the ACQUILEX lexical knowledge base (LKB) system and its use in the representation of lexicons extracted semi-automatically from machine-readable dictionaries.

ThisbookdiscusseshowTypeLogicalGrammarcanbemodi?edinsuch awaythatasystematictreatmentofanaphoraphenomenabecomesp- sible without giving up the general architecture of this framework. By Type Logical Grammar, I mean the version of Categorial Grammar that arose out of the work of Lambek, 1958 and Lambek, 1961. There Ca- gorial types are analyzed as formulae of a logical calculus. In particular, the Categorial slashes are interpreted as forms of constructive impli- tion in the sense of Intuitionistic Logic. Such a theory of grammar is per se attractive for a formal linguist who is interested in the interplay between formal logic and the structure of language. What makes L- bekstyleCategorialGrammarevenmoreexcitingisthefactthat(asvan Benthem,1983pointsout)theCurry-Howardcorrespondence-acentral part of mathematical proof theory which establishes a deep connection betweenconstructivelogicsandthe?-calculus-suppliesthetypelogical syntax with an extremely elegant and independently motivated interface to model-theoretic semantics. Prima facie, anaphora does not 't very well into the Categorial picture of the syntax-semantics interface. The Curry-Howard based composition of meaning operates in a local way, and meaning ass- bly is linear, i.e., every piece of lexical meaning is used exactly once. Anaphora, on the other hand, is in principle unbounded, and it involves by de?nition the multiple use of certain semantic resources. The latter problem has been tackled by several Categorial grammarians by ass- ing su?ciently complex lexical meanings for anaphoric expressions, but the locality problem is not easy to solve in a purely lexical way.

This book constitutes the refereed proceedings of the 4th Language and Technology Conference: Challenges for Computer Science and Linguistics, LTC 2009, held in Poznan, Poland, in November 2009. The 52 revised and in many cases substantially extended papers presented in this volume were carefully reviewed and selected from 103 submissions. The contributions are organized in topical sections on speech processing, computational morphology/lexicography, parsing, computational semantics, dialogue modeling and processing, digital language resources, WordNet, document processing, information processing, and machine translation.

This two-volume set, consisting of LNCS 6608 and LNCS 6609, constitutes the thoroughly refereed proceedings of the 12th International Conference on Computer Linguistics and Intelligent Processing, held in Tokyo, Japan, in February 2011. The 74 full papers, presented together with 4 invited papers, were carefully reviewed and selected from 298 submissions. The contents have been ordered according to the following topical sections: lexical resources; syntax and parsing; part-of-speech tagging and morphology; word sense disambiguation; semantics and discourse; opinion mining and sentiment detection; text generation; machine translation and multilingualism; information extraction and information retrieval; text categorization and classification; summarization and recognizing textual entailment; authoring aid, error correction, and style analysis; and speech recognition and generation.

The ninth campaign of the Cross-Language Evaluation Forum (CLEF) for European languages was held from January to September 2008. There were seven main eval- tion tracks in CLEF 2008 plus two pilot tasks. The aim, as usual, was to test the p- formance of a wide range of multilingual information access (MLIA) systems or s- tem components. This year, 100 groups, mainly but not only from academia, parti- pated in the campaign. Most of the groups were from Europe but there was also a good contingent from North America and Asia plus a few participants from South America and Africa. Full details regarding the design of the tracks, the methodologies used for evaluation, and the results obtained by the participants can be found in the different sections of these proceedings. The results of the CLEF 2008 campaign were presented at a two-and-a-half day workshop held in Aarhus, Denmark, September 17-19, and attended by 150 resear- ers and system developers. The annual workshop, held in conjunction with the European Conference on Digital Libraries, plays an important role by providing the opportunity for all the groups that have participated in the evaluation campaign to get together comparing approaches and exchanging ideas. The schedule of the workshop was divided between plenary track overviews, and parallel, poster and breakout sessions presenting this year's experiments and discu- ing ideas for the future. There were several invited talks.

th TSD 2009was the 12 eventin the series of InternationalConferenceson Text, Speech andDialoguesupportedbytheInternationalSpeechCommunicationAssociation(ISCA) ? and Czech Society for Cybernetics and Informatics (CSKI). This year, TSD was held in Plzen ? (Pilsen), in the Primavera Conference Center, during September 13-17, 2009 and it was organized by the University of West Bohemia in Plzen ? in cooperation with Masaryk University of Brno, Czech Republic. Like its predecessors, TSD 2009 hi- lighted to both the academic and scienti?c world the importance of text and speech processing and its most recent breakthroughsin current applications. Both experienced researchers and professionals as well as newcomers to the text and speech processing ?eld, interested in designing or evaluating interactive software, developing new int- action technologies, or investigatingoverarchingtheories of text and speech processing found in the TSD conference a forum to communicate with people sharing similar - terests. The conference is 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 - quaintedwith currentactivitiesin all aspects oflanguagecommunicationand to witness the amazing vitality of researchers from developing countries too. This year's conference was partially oriented toward semantic processing, which was chosen as the main topic of the conference. All invited speakers (Frederick Jelinek, Louise Guthrie, Roberto Pieraccini, Tilman Becker, and Elmar Not ] h) gave lectures on thenewestresultsintherelativelybroadandstillunexploredareaofsemanticprocessing."

Marcus Contextual Grammars is the first monograph to present a class of grammars introduced about three decades ago, based on the fundamental linguistic phenomenon of strings-contexts interplay (selection). Most of the theoretical results obtained so far about the many variants of contextual grammars are presented with emphasis on classes of questions with relevance for applications in the study of natural language syntax: generative powers, descriptive and computational complexity, automata recognition, semilinearity, structure of the generated strings, ambiguity, regulated rewriting, etc. Constant comparison with families of languages in the Chomsky hierarchy is made. Connections with non-linguistic areas are established, such as molecular computing. Audience: Researchers and students in theoretical computer science (formal language theory and automata theory), computational linguistics, mathematical methods in linguistics, and linguists interested in formal models of syntax.

This book offers a state-of-the-art survey of methods and techniques for structuring, acquiring and maintaining lexical resources for speech and language processing. The first chapter provides a broad survey of the field of computational lexicography, introducing most of the issues, terms and topics which are addressed in more detail in the rest of the book. The next two chapters focus on the structure and the content of man-made lexicons, concentrating respectively on (morpho-)syntactic and (morpho-)phonological information. Both chapters adopt a declarative constraint-based methodology and pay ample attention to the various ways in which lexical generalizations can be formalized and exploited to enhance the consistency and to reduce the redundancy of lexicons. A complementary perspective is offered in the next two chapters, which present techniques for automatically deriving lexical resources from text corpora. These chapters adopt an inductive data-oriented methodology and focus also on methods for tokenization, lemmatization and shallow parsing. The next three chapters focus on speech applications, more specifically on the organization of speech data bases, and on the use of lexica in speech synthesis and speech recognition. The last chapter takes a psycholinguistic perspective and addresses the relation between storage and computation in the mental lexicon. The relevance of these topics for speech and language processing is obvious, for since NLP systems need large lexica in order to achieve reasonable coverage, and since the construction and maintenance of large-size lexical resources is a complex and costly task, it is of crucial importance for those who design or build such systems to be aware of the latest developments in this fast-moving field. The intended audience for this book includes advanced students and professional scientists working in the areas of computational linguistics and language and speech technology.

This book is based on contributions to the Seventh European Summer School on Language and Speech Communication that was held at KTH in Stockholm, Sweden, in July of 1999 under the auspices of the European Language and Speech Network (ELSNET). The topic of the summer school was "Multimodality in Language and Speech Systems" (MiLaSS). The issue of multimodality in interpersonal, face-to-face communication has been an important research topic for a number of years. With the increasing sophistication of computer-based interactive systems using language and speech, the topic of multimodal interaction has received renewed interest both in terms of human-human interaction and human-machine interaction. Nine lecturers contri buted to the summer school with courses on specialized topics ranging from the technology and science of creating talking faces to human-human communication, which is mediated by computer for the handicapped. Eight of the nine lecturers are represented in this book. The summer school attracted more than 60 participants from Europe, Asia and North America representing not only graduate students but also senior researchers from both academia and industry."

The present volume contributes to the growing body of work on sentence pro- cessing. The goal of work in this area is to construct a theory of human sen- tence processing in general, i.e., given a grammar of some particular language and a general characterization of the human sentence processing mechanisms, the particular processing system for that language should follows automati- cally. At least that's the goal. What is needed in order to pursue this goal is systematic in-depth analysis of the sentence routines of individual languages. With respect to German, that is precisely what the present volume delivers. In sharp contrast to a decade ago, the study of German sentence process- ing is flourishing today. Four lively and active centers have emerged. The University of Freiburg is one prominent center, represented in the present vol- ume by the editors Barbara Hemforth and Lars Konieczny (who was at Freiburg for many years) as well as by Christoph Scheepers (who is now in Glasgow) and Christoph Holscher. The University of Potsdam has recently begun an interdisciplinary collaboration on sentence processing involving Matthias Schlesewsky, Gisbert Fanselow, Reinhold Kliegl and Josef Krems. The University of Jena has several investigators trained in linguistics and interested in language processing. That group is represented here by Markus Bader and also includes his colleagues Michael Meng and Josef Bayer.

This book explains how to build Natural Language Generation (NLG) systems - computer software systems which use techniques from artificial intelligence and computational linguistics to automatically generate understandable texts in English or other human languages, either in isolation or as part of multimedia documents, Web pages, and speech output systems. Typically starting from some non-linguistic representation of information as input, NLG systems use knowledge about language and the application domain to automatically produce documents, reports, explanations, help messages, and other kinds of texts. The book covers the algorithms and representations needed to perform the core tasks of document planning, microplanning, and surface realization, using a case study to show how these components fit together. It also discusses engineering issues such as system architecture, requirements analysis, and the integration of text generation into multimedia and speech output systems.

The eleven chapters of this book represent an original contribution to the field of multimodal spoken dialogue systems. The material includes highly relevant topics, such as dialogue modeling in research systems versus industrial systems. The book contains detailed application studies, including speech-controlled MP3 players in a car environment, negotiation training with a virtual human in a military context and the application of spoken dialogue to question-answering systems.

A primary problem in the area of natural language processing has been that of semantic analysis. This book aims to look at the semantics of natural languages in context. It presents an approach to the computational processing of English text that combines current theories of knowledge representation and reasoning in Artificial Intelligence with the latest linguistic views of lexical semantics. This results in distinct advantages for relating the semantic analysis of a sentence to its context. A key feature is the clear separation of the lexical entries that represent the domain-specific linguistic information from the semantic interpreter that performs the analysis. The criteria for defining the lexical entries are firmly grounded in current linguistic theories, facilitating integration with existing parsers. This approach has been implemented and tested in Prolog on a domain for physics word problems and full details of the algorithms and code are presented. Semantic Processing for Finite Domains will appeal to postgraduates and researchers in computational linguistics, and to industrial groups specializing in natural language processing.

Automatic Text Categorization and Clustering are becoming more and more important as the amount of text in electronic format grows and the access to it becomes more necessary and widespread. Well known applications are spam filtering and web search, but a large number of everyday uses exist (intelligent web search, data mining, law enforcement, etc.) Currently, researchers are employing many intelligent techniques for text categorization and clustering, ranging from support vector machines and neural networks to Bayesian inference and algebraic methods, such as Latent Semantic Indexing. This volume offers a wide spectrum of research work developed for intelligent text categorization and clustering. In the following, we give a brief introduction of the chapters that are included in this book.

In both the linguistic and the language engineering community, the creation and use of annotated text collections (or annotated corpora) is currently a hot topic. Annotated texts are of interest for research as well as for the development of natural language pro cessing (NLP) applications. Unfortunately, the annotation of text material, especially more interesting linguistic annotation, is as yet a difficult task and can entail a substan tial amount of human involvement. Allover the world, work is being done to replace as much as possible of this human effort by computer processing. At the frontier of what can already be done (mostly) automatically we find syntactic wordclass tagging, the annotation of the individual words in a text with an indication of their morpho syntactic classification. This book describes the state of the art in syntactic wordclass tagging. As an attempt to give an overall view of the field, this book is of interest to (at least) two, possibly very different, types of reader. The first type consists of those people who are using, or are planning to use, tagged material and taggers. They will want to know what the possibilities and impossibilities of tagging are, but are not necessarily interested in the internal working of automatic taggers. This, on the other hand, is the main interest of our second type of reader, the builders of automatic taggers and other natural language processing software."

Natural Language Processing and Text Mining not only discusses applications of Natural Language Processing techniques to certain Text Mining tasks, but also the converse, the use of Text Mining to assist NLP. It assembles a diverse views from internationally recognized researchers and emphasizes caveats in the attempt to apply Natural Language Processing to text mining. This state-of-the-art survey is a must-have for advanced students, professionals, and researchers.

This book presents a critical overview of current work on linguistic features and establishes new bases for their use in the study and understanding of language.
Features are fundamental components of linguistic description: they include gender (feminine, masculine, neuter); number (singular, plural, dual); person (1st, 2nd, 3rd); tense (present, past, future); and case (nominative, accusative, genitive, ergative). Despite their ubiquity and centrality in linguistic description, much remains to be discovered about them: there is, for example, no readily available inventory showing which features are found in which of the world's languages; there is no consensus about how they operate across different components of language; and there is no certainty about how they interact. This book seeks at once to highlight and to tackle these problems. It brings together perspectives from phonology to formal syntax and semantics, expounding the use of linguistic features in typology, computer applications, and logic. Linguists representing different standpoints spell out clearly the assumptions they bring to different kinds of feature and describe how they use them. Their contrasting contributions highlight the areas of difference and the common ground between their perspectives.
The book brings together original work by leading international scholars. It will appeal to linguists of all theoretical persuasions.

This is a collection of new papers by leading researchers on natural language parsing. In the past, the problem of how people parse the sentences they hear - determine the identity of the words in these sentences and group these words into larger units - has been addressed in very different ways by experimental psychologists, by theoretical linguists, and by researchers in artificial intelligence, with little apparent relationship among the solutions proposed by each group. However, because of important advances in all these disciplines, research on parsing in each of these fields now seems to have something significant to contribute to the others, as this volume demonstrates. The volume includes some papers applying the results of experimental psychological studies of parsing to linguistic theory, others which present computational models of parsing, and a mathematical linguistics paper on tree-adjoining grammars and parsing.

This book teaches the principles of natural language processing and covers linguistics issues. It also details the language-processing functions involved, including part-of-speech tagging using rules and stochastic techniques. A key feature of the book is the author's hands-on approach throughout, with extensive exercises, sample code in Prolog and Perl, and a detailed introduction to Prolog. The book is suitable for researchers and students of natural language processing and computational linguistics.

People often mean more than they say. Grammar on its own is typically insufficient for determining the full meaning of an utterance; the assumption that the discourse is coherent or 'makes sense' has an important role to play in determining meaning as well. Logics of Conversation presents a dynamic semantic framework called Segmented Discourse Representation Theory, or SDRT, where this interaction between discourse coherence and discourse interpretation is explored in a logically precise manner. Combining ideas from dynamic semantics, commonsense reasoning and speech act theory, SDRT uses its analysis of rhetorical relations to capture intuitively compelling implicatures. It provides a computable method for constructing these logical forms and is one of the most formally precise and linguistically grounded accounts of discourse interpretation currently available. The book will be of interest to researchers and students in linguistics and in philosophy of language.