%{search_type} search results

• Preface xiii Chapter 1. LMF
• Historical Context and Perspectives 1 Nicoletta CALZOLARI, Monica MONACHINI and Claudia SORIA 1.1. Introduction 1 1.2. The context 2 1.3. The foundations: the Grosseto Workshop and the "X-Lex" projects 4 1.4. EAGLES and ISLE . 5 1.5. Setting up methodologies and principles for standards 6 1.6. EAGLES/ISLE legacy 10 1.7. Interoperability: the keystone of the field 14 1.8. Bibliography 15 Chapter 2. Model Description 19 Gil FRANCOPOULO and Monte GEORGE 2.1. Objectives 19 2.2. The ISO specification 19 2.3. Means of description 20 2.4. Core model 21 2.5. Core model and extension packages 22 2.6. Morphology extension 23 2.7. Machine-Readable Dictionary extension 26 2.8. NLP syntax extension 27 2.9. NLP semantic extension 29 2.10. Multilingual notation extension 31 2.11. NLP morphological pattern extension 33 2.12. NLP multiword expression pattern extension 36 2.13. Constraint expression extension 38 2.14. Conclusion 39 2.15. Bibliography 40 Chapter 3. LMF and the Data Category Registry: Principles and Application 41 Menzo WINDHOUWER and Sue Ellen WRIGHT 3.1. Introduction 41 3.2. Data category specifications 42 3.3. The ISOcat Data Category Registry 44 3.3.1. A web user interface 44 3.4. LMF and data categories 45 3.5. Conclusions and future work 49 3.6. Bibliography 49 Chapter 4. Wordnet-LMF: A Standard Representation for Multilingual Wordnets 51 Piek VOSSEN, Claudia SORIA and Monica MONACHINI 4.1. Introduction 51 4.2. The KYOTO project 52 4.3. LMF and Wordnet representation 54 4.4. Wordnet-LMF 56 4.5. Conclusions 62 4.6. Bibliography 65 Chapter 5. Prolmf: A Multilingual Dictionary of Proper Names and their Relations 67 Denis MAUREL, Beatrice BOUCHOU-MARKHOFF 5.1. Motivation 67 5.2. Prolmf basis 69 5.3. More on lexica and relations in Prolmf 73 5.4. Conclusion 77 5.5. Bibliography 79 5.6. Appendix 80 Chapter 6. LMF for Arabic 83 Aida KHEMAKHEM, Bilel GARGOURI, Kais HADDAR and Abdelmajid BEN HAMADOU 6.1. Introduction 83 6.2. Modeling of the basic properties 85 6.3. Modeling of the morphologic extension 86 6.4. Modeling of the morphologic pattern extension 88 6.5. Modeling of the syntactic extension 90 6.6. Modeling of the semantic extension 92 6.7. Arabic LMF applications 94 6.8. Implementation 95 6.9. Conclusion 96 6.10. Bibliography 96 Chapter 7. LMF for a Selection of African Languages 99 Chantal ENGUEHARD and Mathieu MANGEOT 7.1. Introduction 99 7.2. Less-resourced languages 99 7.3. From published dictionaries to LMF 102 7.4. Illustrations 104 7.5. Difficulties and proposals 113 7.6. Conclusion 117 7.7. Acknowledgments 117 7.8. Bibliography 117 Chapter 8. LMF and its Implementation in Some Asian Languages 119 Takenobu TOKUNAGA, Sophia Y.M. LEE, Virach SORNLERTLAMVANICH, Kiyoaki SHIRAI, Shu-Kai HSIEH and Chu-Ren HUANG 8.1. Introduction 119 8.2. Lexical specification and data categories 120 8.3. Upper-layer ontology 125 8.4. Evaluation platform 126 8.5. Discussion 128 8.6. Conclusion 129 8.7. Acknowledgments 130 8.8. Bibliography 131 Chapter 9. DUELME: Dutch Electronic Lexicon of Multiword Expressions 133 Jan ODIJK 9.1. Introduction 133 9.2. DUELME 134 9.3. LMF 135 9.4. The DUELME class model 135 9.5. Comparison with the LMF Core Package 137 9.6. Comparison with the LMF NLP multiword expression patterns extension 139 9.7. Conclusions 142 9.8. Acknowledgments 143 9.9. Bibliography 143 Chapter 10. UBY-LMF
• Exploring the Boundaries of Language-Independent Lexicon Models 145 Judith ECKLE-KOHLER, Iryna GUREVYCH, Silvana HARTMANN, Michael MATUSCHEK and Christian M. MEYER 10.1. Introduction 145 10.2. Architecture of UBY-LMF 147 10.3. Language independence of UBY-LMF 148 10.4. FrameNet in UBY-LMF 151 10.5. Conclusion 153 10.6. Acknowledgments 154 10.7. Bibliography 154 Chapter 11. Conversion of Lexicon-Grammar Tables to LMF: Application to French 157 Eric LAPORTE, Elsa TOLONE and Matthieu CONSTANT 11.1. Motivation 157 11.2. The Lexicon-Grammar 157 11.3. Lexical entries 160 11.4. Subcategorization frames 163 11.5. Results 170 11.6. Conclusion 171 11.7. Bibliography 172 Chapter 12. Collaborative Tools: From Wiktionary to LMF, for Synchronic and Diachronic Language Data 175 Thierry DECLERCK, Pirsoka LENDVAI and Karlheinz MORTH 12.1. Introduction 175 12.2. Wiktionary 175 12.3. Related work 177 12.4. Additional challenges: how to encode the diversity of Wiktionary lexicon in LMF? 179 12.5. Conclusion 183 12.6. Bibliography 184 Chapter 13. LMF Experiments on Format Conversions for Resource Merging: Converters and Problems 187 Marta VILLEGAS, Muntsa PADRO and Nuria BEL 13.1. Introduction 187 13.2. Automatic merging of resources 188 13.3. Moving from PAROLE Genelex to LMF 191 13.4. Conclusion 197 13.5. Availability of resources 198 13.6. Bibliography 198 Chapter 14. LMF as a Foundation for Servicized Lexical Resources 201 Yoshihiko HAYASHI, Monica MONACHINI, Bora SAVAS, Claudia SORIA and Nicoletta CALZOLARI 14.1. Introduction 201 14.2. Lexical resources as lexical Web services 201 14.3. LMF-aware Web services in the RESTful style 202 14.4. Implementation showcases 203 14.5. Summary 212 14.6. Bibliography 212 Chapter 15. Creating a Serialization of LMF: The Experience of the RELISH Project 215 Menzo WINDHOUWER, Justin PETRO, Irina NEVSKAYA, Sebastian DRUDE, Helen ARISTAR-DRY and Jost GIPPERT 15.1. Introduction . . 215 15.2. Overview of the RELISH interchange format 216 15.3. Mapping of equivalent elements 217 15.4. Complex mappings 219 15.5. Harmonization of linguistic concepts 223 15.6. Conclusions and future work 224 15.7. Bibliography 225 Chapter 16. Global Atlas: Proper Nouns, From Wikipedia to LMF 227 Gil FRANCOPOULO, Frederic MARCOUL, David CAUSSE and Gregory PIPARO 16.1. Motivation 227 16.2. Preparing recognition 227 16.3. Context of usage 230 16.4. Ontology of types 231 16.5. Main source: Wikipedia 232 16.6. Extraction 233 16.7. Auxiliary machine learning 234 16.8. LMF structures 234 16.9. Example 235 16.10. Results 237 16.11. Current limitations and planned improvements 237 16.12. LMF limitations 238 16.13. Related work 238 16.14. Conclusion 239 16.15. Bibliography 239 Chapter 17. LMF in U.S. Government Language Resource Management 243 Monte GEORGE 17.1. Introduction 243 17.2. Wordscape overview 244 17.3. The goal 245 17.4. The importance of data standards 245 17.5. Language base exchange 246 17.6. Managing multilingual representations 249 17.7. Managing grammatical information 251 17.8. Grammatical information, an MRD example 255 17.9. Managing LBX schema and document instances 258 17.10. Data exchange using LBX 259 17.11. Summary 260 List of Authors 263 Index 267.
• (source: Nielsen Book Data)

The community responsible for developing lexicons for Natural Language Processing (NLP) and Machine Readable Dictionaries (MRDs) started their ISO standardization activities in 2003. These activities resulted in the ISO standard -- Lexical Markup Framework (LMF). After selecting and defining a common terminology, the LMF team had to identify the common notions shared by all lexicons in order to specify a common skeleton (called the core model) and understand the various requirements coming from different groups of users. The goals of LMF are to provide a common model for the creation and use of lexical resources, to manage the exchange of data between and among these resources, and to enable the merging of a large number of individual electronic resources to form extensive global electronic resources. The various types of individual instantiations of LMF can include monolingual, bilingual or multilingual lexical resources. The same specifications can be used for small and large lexicons, both simple and complex, as well as for both written and spoken lexical representations. The descriptions range from morphology, syntax and computational semantics to computer-assisted translation. The languages covered are not restricted to European languages, but apply to all natural languages. The LMF specification is now a success and numerous lexicon managers currently use LMF in different languages and contexts. This book starts with the historical context of LMF, before providing an overview of the LMF model and the Data Category Registry, which provides a flexible means for applying constants like /grammatical gender/ in a variety of different settings. It then presents concrete applications and experiments on real data, which are important for developers who want to learn about the use of LMF. Contents 1. LMF -- Historical Context and Perspectives, Nicoletta Calzolari, Monica Monachini and Claudia Soria. 2. Model Description, Gil Francopoulo and Monte George. 3. LMF and the Data Category Registry: Principles and Application, Menzo Windhouwer and Sue Ellen Wright. 4. Wordnet-LMF: A Standard Representation for Multilingual Wordnets, Piek Vossen, Claudia Soria and Monica Monachini. 5. Prolmf: A Multilingual Dictionary of Proper Names and their Relations, Denis Maurel, Beatrice Bouchou-Markhoff. 6. LMF for Arabic, Aida Khemakhem, Bilel Gargouri, Kais Haddar and Abdelmajid Ben Hamadou. 7. LMF for a Selection of African Languages, Chantal Enguehard and Mathieu Mangeot. 8. LMF and its Implementation in Some Asian Languages, Takenobu Tokunaga, Sophia Y.M. Lee, Virach Sornlertlamvanich, Kiyoaki Shirai, Shu-Kai Hsieh and Chu-Ren Huang. 9. DUELME: Dutch Electronic Lexicon of Multiword Expressions, Jan Odijk. 10. UBY-LMF -- Exploring the Boundaries of Language-Independent Lexicon Models, Judith Eckle-Kohler, Iryna Gurevych, Silvana Hartmann, Michael Matuschek and Christian M. Meyer. 11. Conversion of Lexicon-Grammar Tables to LMF: Application to French, Eric Laporte, Elsa Tolone and Matthieu Constant. 12. Collaborative Tools: From Wiktionary to LMF, for Synchronic and Diachronic Language Data, Thierry Declerck, Pirsoka Lendvai and Karlheinz Morth. 13. LMF Experiments on Format Conversions for Resource Merging: Converters and Problems, Marta Villegas, Muntsa Padro and Nuria Bel. 14. LMF as a Foundation for Servicized Lexical Resources, Yoshihiko Hayashi, Monica Monachini, Bora Savas, Claudia Soria and Nicoletta Calzolari. 15. Creating a Serialization of LMF: The Experience of the RELISH Project, Menzo Windhouwer, Justin Petro, Irina Nevskaya, Sebastian Drude, Helen Aristar-Dry and Jost Gippert. 16. Global Atlas: Proper Nouns, From Wikipedia to LMF, Gil Francopoulo, Frederic Marcoul, David Causse and Gregory Piparo. 17. LMF in U.S. Government Language Resource Management, Monte George. About the Authors Gil Francopoulo works for Tagmatica (www.tagmatica.com), a company specializing in software development in the field of linguistics and documentation in the semantic web, in Paris, France, as well as for Spotter (www.spotter.com), a company specializing in media and social media analytics.
(source: Nielsen Book Data)

• Acknowledgments ix Introduction xi
• Part 1 Applicative and Scientific Context 1
• Chapter 1 Leveraging Comparable Corpora and Computer-Assisted Translation 3
• Chapter 2 User-Centered Evaluation of Lexicons Extracted from Comparable Corpora 41
• Chapter 3 Automatic Generation of Term Translations 67
• Part 2 Contributions to Compositional Translation 99
• Chapter 4 Morph-Compositional Translation: Methodological Framework 101
• Chapter 5 Experimental Data 123
• Chapter 6 Formalization and Evaluation of Candidate Translation Generation 139
• Chapter 7 Formalization and Evaluation of Candidate Translation Ranking 179 Conclusion and Perspectives 199
• Part 3 Appendices 205
• Appendix 1 Measures 207
• Appendix 2 Data 215
• Appendix 3 Comparable Corpora Lexicons Consultation Interface 261 List of Tables 265 List of Figures 271 List of Algorithms 273 List of Extracts 275 Bibliography 277 Index 289.
• (source: Nielsen Book Data)

Computer-assisted translation (CAT) has always used translation memories, which require the translator to have a corpus of previous translations that the CAT software can use to generate bilingual lexicons. This can be problematic when the translator does not have such a corpus, for instance, when the text belongs to an emerging field. To solve this issue, CAT research has looked into the leveraging of comparable corpora, i.e. a set of texts, in two or more languages, which deal with the same topic but are not translations of one another. This work had two primary objectives. The first is to assess the input of lexicons extracted from comparable corpora in the context of a specialized human translation task. The second objective is to identify bilingual-lexicon-extraction methods which best match the translators' needs, determining the current limits of these techniques and suggesting improvements. The author focuses, in particular, on the identification of fertile translations, the management of multiple morphological structures, and the ranking of candidate translations. The experiments are carried out on two language pairs (English-French and English-German) and on specialized texts dealing with breast cancer. This research puts significant emphasis on applicability - methodological choices are guided by the needs of the final users. This book is organized in two parts: the first part presents the applicative and scientific context of the research, and the second part is given over to efforts to improve compositional translation. The research work presented in this book received the PhD Thesis award 2014 from the French association for natural language processing (ATALA).
(source: Nielsen Book Data)

In this paper, we described the PNNL Word Sense Disambiguation system as applied to the English All-Word task in Se-mEval 2007. We use a supervised learning approach, employing a large number of features and using Information Gain for dimension reduction. Our Maximum Entropy approach combined with a rich set of features produced results that are significantly better than baseline and are the highest F-score for the fined-grained English All-Words subtask.

The Rehabilitation Engineering Research Center on Universal Design and the Built Environment (RERC-UD), a federally funded research center located in The University at Buffalo, hosted a series of State of the Science (SOS) Activities in 2008. The SOS activities generated a large number of papers on both research and the practice of universal design in community infrastructures, public buildings, and housing. This Ebook contains a selected group of these papers that provide a survey of notable developments in the field, reflections on how research and practice can be advanced further, and propose an agenda for the near future. It is hoped that the book will be found useful for researchers, students and practitioners in this field.

• Fundamentals of Dialogue Systems
• First-Order Logic
• Logic-Based Domain Modelling
• Interactive Model Generation
• A Prototype Based on VoiceXML
• Information State-Based Dialogue Management
• Revised Prototype and System Architecture.

Reasoning for Information: Seeking and Planning Dialogues provides a logic-based reasoning component for spoken language dialogue systems. This component, called Problem Assistant is responsible for processing constraints on a possible solution obtained from various sources, namely user and the system's domain-specific information. The authors also present findings on the implementation of a dialogue management interface to the Problem Assistant. The dialogue system supports simple mixed-initiative planning interactions in the TRAINS domain, which is still a relatively complex domain involving.

• Compositional Semantics and Generative Grammar
• Mathematics of Syntactic Structure
• Elements of Proof Theory
• Variants of the Lambek Calculus
• Grammatical Reasoning
• Minimalist Derivations
• Continuations and Contexts
• Towards Dynamics of Meaning
• Interaction and Dialogue.
• (source: Nielsen Book Data)

This book presents several recent advances in natural language semantics and explores the boundaries between syntax and semantics over the last two decades. It is based on some of the most recent theories in logic, such as linear logic and ludics, first created by Jean-Yves Girard, and it also provides some sharp analyses of computational semantical representations, explaining advanced theories in theoretical computer sciences, such as the lambda-mu and Lambek-Grishin calculi which were applied by Philippe de Groote and Michael Moortgat. The author also looks at Aarne Ranta's `proof as meaning' approach, which was first based on Martin-Loef's Type Theory.Meaning, Logic and Ludics surveys the many solutions which have been proposed for the syntax-semantics interface, taking into account the specifications of linguistic signs (continuous or discontinuous) and the fundamental mechanisms developed by linguists and notable Generativists. This pioneering publication also presents ludics (in a chapter co-authored with Myriam Quatrini), a framework which allows us to characterize meaning as an invariant with regard to interaction between processes. It is an excellent book for advanced students, and academics alike, in the field of computational linguistics.
(source: Nielsen Book Data)

• Compositional Semantics and Generative Grammar
• Mathematics of Syntactic Structure
• Elements of Proof Theory
• Variants of the Lambek Calculus
• Grammatical Reasoning
• Minimalist Derivations
• Continuations and Contexts
• Towards Dynamics of Meaning
• Interaction and Dialogue.
• (source: Nielsen Book Data)

This book presents several recent advances in natural language semantics and explores the boundaries between syntax and semantics over the last two decades. It is based on some of the most recent theories in logic, such as linear logic and ludics, first created by Jean-Yves Girard, and it also provides some sharp analyses of computational semantical representations, explaining advanced theories in theoretical computer sciences, such as the lambda-mu and Lambek-Grishin calculi which were applied by Philippe de Groote and Michael Moortgat. The author also looks at Aarne Ranta's `proof as meaning' approach, which was first based on Martin-Loef's Type Theory.Meaning, Logic and Ludics surveys the many solutions which have been proposed for the syntax-semantics interface, taking into account the specifications of linguistic signs (continuous or discontinuous) and the fundamental mechanisms developed by linguists and notable Generativists. This pioneering publication also presents ludics (in a chapter co-authored with Myriam Quatrini), a framework which allows us to characterize meaning as an invariant with regard to interaction between processes. It is an excellent book for advanced students, and academics alike, in the field of computational linguistics.
(source: Nielsen Book Data)

• 1. Memory-based learning in natural language processing
• 2. Inspirations from linguistics and artificial intelligence
• 3. Memory and similarity
• 4. Application to morpho-phonology
• 5. Application to shallow parsing
• 6. Abstraction and generalization
• 7. Extensions.
• (source: Nielsen Book Data)

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.
(source: Nielsen Book Data)

• Part I. Fundamental Aspects: 1. Ontology and the lexicon: a multi-disciplinary perspective Laurent Prevot, Chu-Ren Huang, Nicoletta Calzolari, Aldo Gangemi, Alessandro Lenci and Alessandro Oltramari
• 2. Formal ontology as interlingua: the SUMO and WordNet linking project and GlobalWordNet Adam Pease and Christiane Fellbaum
• 3. Interfacing WordNet with DOLCE: towards OntoWordNet Aldo Gangemi, Nicola Guarino, Claudio Masolo and Alessandro Oltramari
• 4. Reasoning over natural language text by means of FrameNet and ontologies Jan Scheffczyk, Collin F. Baker and Srini Narayanan
• 5. Synergizing ontologies and the lexicon: a roadmap Alessandro Oltramari, Aldo Gangemi, Chu-Ren Huang, Nicoletta Calzolari, Alessandro Lenci and Laurent Prevot
• Part II. Discovery and Representation of Conceptual Systems: 6. Experiments of ontology construction with formal concept analysis SuJian Li, Qin Lu and Wenjie Li
• 7. Ontology, lexicon, and fact repository as leveraged to interpret events of change Marjorie McShane, Sergei Nirenburg and Stephen Beale
• 8. Hantology: conceptual system discovery based on orthographic convention Ya-Min Chou and Chu-Ren Huang
• 9. What's in a schema? A formal metamodel for ECG and FrameNet Aldo Gangemi
• Part III. Interfacing Ontologies and Lexical Resources: 10. Interfacing ontologies and lexical resources Laurent Prevot, Stefano Borgo and Alessandro Oltramari
• 11. Sinica BOW (Bilingual Ontological WordNet): integration of BilingualWord-Net and SUMO Chu-Ren Huang, Ru-Yng Chang and Hsiang-bin Lee
• 12. Ontology-based semantic lexicons: mapping between terms and object descriptions Paul Buitelaar
• 13. Merging global and specialized linguistic ontologies Manuela Speranza and Bernardo Magnini
• Part IV. Learning and Using Ontological Knowledge: 14. The life cycle of knowledge Alessandro Lenci
• 15. The omega ontology Andrew Philpot, Eduard Hovy and Patrick Pantel
• 16. Automatic acquisition of lexico-semantic knowledge for question answering Lonneke van der Plas, Gosse Bouma and Jori Mur
• 17. Agricultural ontology construction and maintenance in Thai Asanee Kawtrakul and Aurawan Imsombut.
• (source: Nielsen Book Data)

The relation between ontologies and language is currently at the forefront of natural language processing (NLP). Ontologies, as widely used models in semantic technologies, have much in common with the lexicon. A lexicon organizes words as a conventional inventory of concepts, while an ontology formalizes concepts and their logical relations. A shared lexicon is the prerequisite for knowledge-sharing through language, and a shared ontology is the prerequisite for knowledge-sharing through information technology. In building models of language, computational linguists must be able to accurately map the relations between words and the concepts that they can be linked to. This book focuses on the technology involved in enabling integration between lexical resources and semantic technologies. It will be of interest to researchers and graduate students in NLP, computational linguistics, and knowledge engineering, as well as in semantics, psycholinguistics, lexicology and morphology/syntax.
(source: Nielsen Book Data)

• Syntax and syntactic analysis
• Semantics and semantic analysis.-Spoken language and dialogue
• Corpora and corpus-based language processing
• Text and message understanding
• Information extraction and text mining
• Information retrieval and question answering
• Language learning
• Machine translation.

This book constitutes the refereed proceedings of the 14th International Conference of the Pacific Association for Computational Linguistics, PACLING 2015, held in Bali, Indonesia, in May 2015. The 18 revised full papers presented were carefully reviewed and selected from 45 papers. The papers are organized around the following topics: syntax and syntactic analysis; semantics and semantic analysis; spoken language and dialogue; corpora and corpus-based language processing; text and message understanding; information extraction and text mining; information retrieval and question answering; language learning; machine translation.

• 1. Introduction
• 2. A brief history of causality
• 3. Probability, logic and probabilistic temporal logic
• 4. Defining causality
• 5. Inferring causality
• 6. Token causality
• 7. Case studies
• 8. Conclusion
• Appendix A. A little bit of statistics
• Appendix B. Proofs.
• (source: Nielsen Book Data)

Causality is a key part of many fields and facets of life, from finding the relationship between diet and disease to discovering the reason for a particular stock market crash. Despite centuries of work in philosophy and decades of computational research, automated inference and explanation remains an open problem. In particular, the timing and complexity of relationships has been largely ignored even though this information is critically important for prediction, explanation and intervention. However, given the growing availability of large observational datasets including those from electronic health records and social networks, it is a practical necessity. This book presents a new approach to inference (finding relationships from a set of data) and explanation (assessing why a particular event occurred), addressing both the timing and complexity of relationships. The practical use of the method developed is illustrated through theoretical and experimental case studies, demonstrating its feasibility and success.
(source: Nielsen Book Data)

• 1. Sociality
• 2. Conditioning
• 3. Solutions
• 4. Coordination
• 5. Uncertainty
• 6. Satisficing
• 7. Applications
• 8. Conclusion.
• (source: Nielsen Book Data)

Game theory explains how to make good choices when different decision makers have conflicting interests. The classical approach assumes that decision makers are committed to making the best choices for themselves regardless of the effect on others, but such an approach is less appropriate when cooperation, compromise and negotiation are important. This book describes conditional games, a form of game theory that accommodates multiple stakeholder decision-making scenarios where cooperation and negotiation are significant issues and where notions of concordant group behavior are important. Using classical binary preference relations as a point of departure, the book extends the concept of a preference ordering that permits stakeholders to modulate their preferences as functions of the preferences of others. As these conditional preferences propagate through a group of decision makers, they create social bonds that lead to notions of group concordance. This book is intended for all students and researchers of decision theory and game theory.
(source: Nielsen Book Data)

• Preface.- Chapter 1 Introduction. 1.1 Objectives and Rationale of the Book. 1.2 Why Do We Need to Go Beyond Raw Corpora. 1.3 What is Corpus Annotation. 1.4 Organization of the Book.- Chapter 2 Text Processing with the Command Line Interface. 2.1 The Command Line Interface. 2.2 Basic Commands. 2.2.1 Notational Conventions. 2.2.2 Printing the Current Working Directory. 2.2.3 Listing Files and Subdirectories. 2.2.4 Making New Directories. 2.2.5 Changing Directory Locations. 2.2.6
• Creating and Editing Text Files with UTF-8 Encoding. 2.2.7 Viewing, Renaming, Moving, Copying, and Removing Files. 2.2.8 Copying, Moving, and Removing Directories. 2.2.9 Using Shell Meta-Characters for File Matching. 2.2.10 Manual Pages, Command History, and Command Line Completion. 2.3 Tools for Text Processing. 2.3.1 Searching for a String with egrep. 2.3.2 Regular Expressions. 2.3.3 Character Translation with tr. 2.3.4 Editing Files from the Command Line with sed. 2.3.5 Data Filtering and Manipulation Using awk. 2.3.6 Task Decomposition and Pipes. 2.4 Summary.- Chapter 3 Lexical Annotation. 3.1 Part-of-Speech Tagging. 3.1.1 What is Part-of-Speech Tagging. 3.1.2 Understanding Part-of-Speech Tagsets. 3.1.3 The Stanford Part-of-Speech Tagger. 3.2 Lemmatization. 3.2.1 What is Lemmatization and Why is it Useful. 3.2.2 The TreeTagger. 3.3 Additional Tools. 3.3.1 The Stanford Tokenizer. 3.3.2 The Stanford Word Segmenter for Arabic and Chinese. 3.3.3 The CLAWS Tagger for English. 3.3.4 The Morpha Lemmatizer for English. 3.4 Summary.- Chapter 4 Lexical Analysis. 4.1 Frequency Lists. 4.1.1 Working with Output Files from the TreeTagger. 4.1.2 Working with Output Files from the Stanford POS Tagger and Morpha. 4.1.3 Analyzing Frequency Lists with Text Processing Tools. 4.2 N-grams. 4.3 Lexical Richness. 4.3.1 Lexical Density. 4.3.2 Lexical Variation. 4.3.3 Lexical Sophistication. 4.3.4 Tools for Lexical Richness Analysis. 4.4 Summary.- Chapter 5 Syntactic Annotation. 5.1 Syntactic Parsing Overview. 5.1.1 What is Syntactic Parsing and Why is it Useful. 5.1.2 Phrase Structure Grammars. 5.1.3 Dependency Grammars. 5.2 Syntactic Parsers. 5.2.1 The Stanford Parser. 5.2.2 Collins' Parser. 5.3 Summary.- Chapter 6 Syntactic Analysis. 6.1 Querying Syntactically Parsed Corpora. 6.1.1 Tree Relationships. 6.1.2 Tregex. 6.2 Syntactic Complexity Analysis.
• 6.2.1 Measures of Syntactic Complexity. 6.2.2 Syntactic Complexity Analyzers. 6.3 Summary.- Chapter 7 Semantic, Pragmatic and Discourse Analysis.- 7.1 Semantic Field Analysis. 7.1.1 The UCREL Semantic Analysis System. 7.1.2 Profile in Semantics-Lexical in Computerized Profiling. 7.2 Analysis of Propositions. 7.2.1 Computerized Propositional Idea Density Rater. 7.2.2 Analysis of Propositions in Computerized Profiling. 7.3 Conversational Act Analysis in Computerized Profiling. 7.4 Coherence and Cohesion Analysis in Coh-Metrix. 7.5 Text Structure Analysis. 7.6 Summary.- Chapter 8 Summary and Outlook. 8.1 Summary of the Book. 8.2 Future Directions in Computational Corpus Analysis. 8.2.1 Computational Analysis of Language Meaning and Use. 8.2.2 Computational Analysis of Learner Language. 8.2.3 Computational Analysis Based on Specific Language Theories.- Appendix.
• (source: Nielsen Book Data)

In the past few decades the use of increasingly large text corpora has grown rapidly in language and linguistics research. This was enabled by remarkable strides in natural language processing (NLP) technology, technology that enables computers to automatically and efficiently process, annotate and analyze large amounts of spoken and written text in linguistically and/or pragmatically meaningful ways. It has become more desirable than ever before for language and linguistics researchers who use corpora in their research to gain an adequate understanding of the relevant NLP technology to take full advantage of its capabilities. This volume provides language and linguistics researchers with an accessible introduction to the state-of-the-art NLP technology that facilitates automatic annotation and analysis of large text corpora at both shallow and deep linguistic levels. The book covers a wide range of computational tools for lexical, syntactic, semantic, pragmatic and discourse analysis, together with detailed instructions on how to obtain, install and use each tool in different operating systems and platforms. The book illustrates how NLP technology has been applied in recent corpus-based language studies and suggests effective ways to better integrate such technology in future corpus linguistics research. This book provides language and linguistics researchers with a valuable reference for corpus annotation and analysis.
(source: Nielsen Book Data)

• Introduction
• Foundation
• Statistical parsing
• Machine translation
• Biological sequence analysis: Basics
• Biological sequence analysis: intersection.

Grammars are gaining importance in natural language processing and computational biology as a means of encoding theories and structuring algorithms. But one serious obstacle to applications of grammars is that formal language theory traditionally classifies grammars according to their weak generative capacity (what sets of strings they generate) and tends to ignore strong generative capacity (what sets of structural descriptions they generate) even though the latter is more relevant to applications. This book develops and demonstrates a framework for carrying out rigorous comparisons of grammar formalisms in terms of their usefulness for applications, focusing on three areas of application: statistical parsing, natural language translation, and biological sequence analysis. These results should pave the way for theoretical research to pursue results that are more directed towards applications, and for practical research to explore the use of advanced grammar formalisms more easily.

• Cover
• Copyright
• Credits
• About the Author
• About the Reviewer
• www.PacktPub.com
• Customer Feedback
• Table of Contents
• Preface
• Chapter 1: Getting Started with Microsoft Cognitive Services
• Cognitive Services in action for fun and life changing purposes
• Setting up boilerplate code
• Detecting faces with the Face API
• Overview of what we are dealing with
• Vision
• Computer Vision
• Emotion
• Face
• Video
• Speech
• Bing Speech
• Speaker Recognition
• Custom Recognition
• Language
• Bing Spell Check
• Language Understanding Intelligent Service (LUIS)
• Linguistic Analysis
• Text Analysis
• Web Language Model
• Knowledge
• Academic
• Entity Linking
• Knowledge Exploration
• Recommendations
• Search
• Bing Web Search
• Bing Image Search
• Bing Video Search
• Bing News Search
• Bing Autosuggest
• Getting feedback on detected faces
• Summary
• Chapter 2: Analyzing Images to Recognize a Face
• Learning what an image is about using Computer Vision API
• Setting up a chapter example project
• Generic image analysis
• Recognizing celebrities using domain models
• Utilizing Optical Character Recognition
• Generating image thumbnails
• Diving deep into the Face API
• Retrieving more information from the detected faces
• Deciding whether two faces belong to the same person
• Finding similar faces
• Grouping similar faces
• Adding identification to our Smart-House application
• Creating our Smart-House application
• Adding people to be identified
• Identifying a person
• Summary
• Chapter 3: Analyzing Videos
• Knowing your mood using the Emotion API
• Getting images from a web camera
• Letting the smart-house know your mood
• Diving into the Video API
• Video operations as common code
• Getting operation results
• Wiring up execution in the ViewModel.

• Detecting and tracking faces in videos
• Detecting motion
• Stabilizing shaky videos
• Generating video thumbnails
• Analyzing emotions in videos
• Summary
• Chapter 4: Letting Applications Understand Commands
• Creating language-understanding models
• Register an account and get a license key
• Creating an application
• Recognizing key data using entities
• Understanding what the user wants using intents
• Simplifying development using pre-built models
• Pre-built applications
• Training a model
• Training and publishing the model
• Connecting to the smart-house application
• Model improvement through active usage
• Visualizing performance
• Resolving performance problems
• Adding model features
• Adding labeled utterances
• Looking for incorrect utterance labels
• Changing the schema
• Active learning
• Executing operations based on commands
• Maintaining conversations from unclear utterances
• Completing actions from intents
• Action fulfillment
• Summary
• Chapter 5: Speak with Your Application
• Converting text to audio and vice versa
• Speaking to the application
• Letting the application speak back
• Audio output format
• Error codes
• Supported languages
• Utilizing LUIS based on spoken commands
• Knowing who is speaking
• Adding speaker profiles
• Enrolling a profile
• Identifying the speaker
• Verifying a person through speech
• Customizing speech recognition
• Creating a custom acoustic model
• Creating a custom language model
• Deploying the application
• Summary
• Chapter 6: Understanding Text
• Setting up a common core
• New project
• Web requests
• Data contracts
• Correcting spelling errors
• Natural Language Processing using the Web Language Model
• Breaking a word into several
• Generating the next word in a sequence of words.

• Learning if a word is likely to follow a sequence of words
• Learning if certain words is likely to appear together
• Extracting information through textual analysis
• Detecting language
• Extracting key phrases from text
• Learning if a text is positive or negative
• Exploring text using linguistic analysis
• Introduction to linguistic analysis
• Analyzing text from a linguistic viewpoint
• Summary
• Chapter 7: Extending Knowledge Based on Context
• Linking entities based on context
• Providing personalized recommendations
• Creating a model
• Importing catalog data
• Importing usage data
• Building a model
• Consuming recommendations
• Recommending items based on prior activities
• Summary
• Chapter 8: Querying Structured Data in a Natural Way
• Tapping into academic content using the Academic API
• Setting up an example project
• Interpreting natural language queries
• Finding academic entities from query expressions
• Calculating the distribution of attributes from academic entities
• Entity attributes
• Creating the backend using the Knowledge Exploration Service
• Defining attributes
• Adding data
• Building the index
• Understanding natural language
• Local hosting and testing
• Going for scale
• Hooking into Microsoft Azure
• Deploying the service
• Answering FAQs using QnA Maker
• Creating a knowledge base from frequently asked questions
• Training the model
• Publishing the model
• Improving the model
• Summary
• Chapter 9: Adding Specialized Searches
• Searching the Web from the Smart-House application
• Preparing the application for web searches
• Searching the Web
• Getting the news
• News from queries
• News from categories
• Trending news
• Searching for images and videos
• Using a common user interface
• Searching for images
• Searching for videos.

• Helping the user with auto suggestions
• Adding Autosuggest to the user interface
• Suggesting queries
• Search commonalities
• Languages
• Pagination
• Filters
• Safe search
• Freshness
• Errors
• Summary
• Chapter 10: Connecting the Pieces
• Connecting the pieces
• Creating an intent
• Updating the code
• Executing actions from intents
• Searching news on command
• Describing news images
• Real-life applications using Microsoft Cognitive Services
• Uber
• DutchCrafters
• CelebsLike.me
• Pivothead
• wearable glasses
• Zero Keyboard
• The common theme
• Where to go from here
• Summary
• Appendix A: LUIS Entities and Intents
• LUIS pre-built intents
• LUIS pre-built entities
• Appendix B: Additional Information on Linguistic Analysis
• Part-of-Speech Tags
• Phrase types
• Appendix C: License Information
• Video Frame Analyzer
• OpenCvSharp3
• Newtonsoft. Json
• NAudio
• Definitions
• Grant of Rights
• Conditions and Limitations
• Index.

Learn to build interactive and efficient applications by leveraging 24 effective cognitive services APIs powered by Microsoft About This Book * Explore the capabilities of 24 of the APIs released as part of the Cognitive Services platform * Build intelligent apps that combine the power of computer vision, speech recognition, and language processing * Give your apps human-like cognitive intelligence with this hands-on guide Who This Book Is For .NET developers who want to add AI capabilities to their applications will find this book useful. No knowledge of machine learning or AI is necessary to work through this book. What You Will Learn * Identify a person through visual inspection and audio * Reduce user effort by utilizing AI-like capabilities * Understand how to analyze images and text in different ways * Find out how to analyze images using Vision APIs * Add video analysis to applications using Vision APIs * Utilize Search to find anything you want * Analyze text to extract information and explore text structure In Detail Microsoft has revamped its Project Oxford to launch the all new Cognitive Services platform-a set of 30 APIs to add speech, vision, language, and knowledge capabilities to apps. This book will introduce you to 24 of the APIs released as part of Cognitive Services platform and show you how to leverage their capabilities. More importantly, you'll see how the power of these APIs can be combined to build real-world apps that have cognitive capabilities. The book is split into three sections: computer vision, speech recognition and language processing, and knowledge and search. You will be taken through the vision APIs at first as this is very visual, and not too complex. The next part revolves around speech and language, which are somewhat connected. The last part is about adding real-world intelligence to apps by connecting them to Knowledge and Search APIs. By the end of this book, you will be in a position to understand what Microsoft Cognitive Service can offer and how to use the different APIs. Style and approach This book takes you through essential API capabilities and shows how to utilize them to suit the needs of your application.
(source: Nielsen Book Data)

• Conversational Interfaces / Oliver Lemon
• Developing Dialogue Managers from Limited Amounts of Data / Verena Rieser, Oliver Lemon
• Data-Driven Methods for Spoken Language Understanding / James Henderson, Filip Jurčíček
• User Simulation in the Development of Statistical Spoken Dialogue Systems / Simon Keizer, Stéphane Rossignol
• Optimisation for POMDP-Based Spoken Dialogue Systems / Milica Gašić, Filip Jurčíček, Blaise Thomson
• Statistical Approaches to Adaptive Natural Language Generation / Oliver Lemon, Srini Janarthanam
• Metrics and Evaluation of Spoken Dialogue Systems / Helen Hastie
• Data-Driven Methods in Industrial Spoken Dialog Systems / Roberto Pieraccini, David Suendermann
• Conclusion and Future Research Directions / Olivier Pietquin.

The EC FP7 project "Computational Learning in Adaptive Systems for Spoken Conversation" (CLASSiC) was a European initiative working on a fully data-driven architecture for the development of conversational interfaces, as well as new machine learning approaches for their sub-components. It developed a variety of novel statistical methods for spoken dialogue processing, for extended conversational interaction, which are now collected together in this book. A major focus of the project was in tracking the accumulation of information about user goals over multiple dialogue turns (i.e. extended conversational interaction), and in maintaining overall system robustness even when speech recognition results contain errors, by managing uncertainty through the processing chain. Other advances were made in the areas of adaptive natural language generation (NLG), statistical methods for spoken language understanding (SLU), and machine learning methods for system optimisation, either during online operation, simulation, or from small amounts of data. This book collects together the main research results and lessons learned in the CLASSiC project. Each chapter provides a summary of the specific methods developed and results obtained in its particular research area. In addition, leading researchers in statistical methods applied to industrial-scale dialogue systems (from SpeechCycle) have contributed a chapter surveying their recent work. This volume will serve as a valuable introduction to the current state-of-the-art in statistical approaches to developing conversational interfaces, for active researchers in the field in industry and academia, as well as for students who are considering working in this exciting area