Theory and Applications of Natural Language Processing - Böcker

This book brings together work on Turkish natural language and speech processing over the last 25 years, covering numerous fundamental tasks ranging from morphological processing and language modeling, to full-fledged deep parsing and machine translation, as well as computational resources developed along the way to enable most of this work. Owing to its complex morphology and free constituent order, Turkish has proved to be a fascinating language for natural language and speech processing research and applications.After an overview of the aspects of Turkish that make it challenging for natural language and speech processing tasks, this book discusses in detail the main tasks and applications of Turkish natural language and speech processing. A compendium of the work on Turkish natural language and speech processing, it is a valuable reference for new researchers considering computational work on Turkish, as well as a one-stop resource for commercialand research institutions planning to develop applications for Turkish. It also serves as a blueprint for similar work on other Turkic languages such as Azeri, Turkmen and Uzbek.

​This book is an excellent introduction to multiword expressions. It provides a unique, comprehensive and up-to-date overview of this exciting topic in computational linguistics. The first part describes the diversity and richness of multiword expressions, including many examples in several languages. These constructions are not only complex and arbitrary, but also much more frequent than one would guess, making them a real nightmare for natural language processing applications. The second part introduces a new generic framework for automatic acquisition of multiword expressions from texts. Furthermore, it describes the accompanying free software tool, the mwetoolkit, which comes in handy when looking for expressions in texts (regardless of the language). Evaluation is greatly emphasized, underlining the fact that results depend on parameters like corpus size, language, MWE type, etc. The last part contains solid experimental results and evaluates the mwetoolkit, demonstrating its usefulness for computer-assisted lexicography and machine translation.This is the first book to cover the whole pipeline of multiword expression acquisition in a single volume. It is addresses the needs of students and researchers in computational and theoretical linguistics, cognitive sciences, artificial intelligence and computer science. Its good balance between computational and linguistic views make it the perfect starting point for anyone interested in multiword expressions, language and text processing in general.

This book comprises a set of articles that specify the methodology of text mining, describe the creation of lexical resources in the framework of text mining and use text mining for various tasks in natural language processing (NLP).

This volume provides an overview of the field of Hybrid Machine Translation (MT) and presents some of the latest research conducted by linguists and practitioners from different multidisciplinary areas. Nowadays, most important developments in MT are achieved by combining data-driven and rule-based techniques. These combinations typically involve hybridization of different traditional paradigms, such as the introduction of linguistic knowledge into statistical approaches to MT, the incorporation of data-driven components into rule-based approaches, or statistical and rule-based pre- and post-processing for both types of MT architectures. The book is of interest primarily to MT specialists, but also – in the wider fields of Computational Linguistics, Machine Learning and Data Mining – to translators and managers of translation companies and departments who are interested in recent developments concerning automated translation tools.

​This book is an excellent introduction to multiword expressions. It provides a unique, comprehensive and up-to-date overview of this exciting topic in computational linguistics. The first part describes the diversity and richness of multiword expressions, including many examples in several languages. These constructions are not only complex and arbitrary, but also much more frequent than one would guess, making them a real nightmare for natural language processing applications. The second part introduces a new generic framework for automatic acquisition of multiword expressions from texts. Furthermore, it describes the accompanying free software tool, the mwetoolkit, which comes in handy when looking for expressions in texts (regardless of the language). Evaluation is greatly emphasized, underlining the fact that results depend on parameters like corpus size, language, MWE type, etc. The last part contains solid experimental results and evaluates the mwetoolkit, demonstrating its usefulness for computer-assisted lexicography and machine translation.This is the first book to cover the whole pipeline of multiword expression acquisition in a single volume. It is addresses the needs of students and researchers in computational and theoretical linguistics, cognitive sciences, artificial intelligence and computer science. Its good balance between computational and linguistic views make it the perfect starting point for anyone interested in multiword expressions, language and text processing in general.

This book comprises a set of articles that specify the methodology of text mining, describe the creation of lexical resources in the framework of text mining and use text mining for various tasks in natural language processing (NLP).

This volume provides an overview of the field of Hybrid Machine Translation (MT) and presents some of the latest research conducted by linguists and practitioners from different multidisciplinary areas. Nowadays, most important developments in MT are achieved by combining data-driven and rule-based techniques. These combinations typically involve hybridization of different traditional paradigms, such as the introduction of linguistic knowledge into statistical approaches to MT, the incorporation of data-driven components into rule-based approaches, or statistical and rule-based pre- and post-processing for both types of MT architectures. The book is of interest primarily to MT specialists, but also – in the wider fields of Computational Linguistics, Machine Learning and Data Mining – to translators and managers of translation companies and departments who are interested in recent developments concerning automated translation tools.

This book brings together work on Turkish natural language and speech processing over the last 25 years, covering numerous fundamental tasks ranging from morphological processing and language modeling, to full-fledged deep parsing and machine translation, as well as computational resources developed along the way to enable most of this work. Owing to its complex morphology and free constituent order, Turkish has proved to be a fascinating language for natural language and speech processing research and applications.After an overview of the aspects of Turkish that make it challenging for natural language and speech processing tasks, this book discusses in detail the main tasks and applications of Turkish natural language and speech processing. A compendium of the work on Turkish natural language and speech processing, it is a valuable reference for new researchers considering computational work on Turkish, as well as a one-stop resource for commercialand research institutions planning to develop applications for Turkish. It also serves as a blueprint for similar work on other Turkic languages such as Azeri, Turkmen and Uzbek.

This book provides an overview of how comparable corpora can be used to overcome the lack of parallel resources when building machine translation systems for under-resourced languages and domains. It presents a wealth of methods and open tools for building comparable corpora from the Web, evaluating comparability and extracting parallel data that can be used for the machine translation task. It is divided into several sections, each covering a specific task such as building, processing, and using comparable corpora, focusing particularly on under-resourced language pairs and domains.The book is intended for anyone interested in data-driven machine translation for under-resourced languages and domains, especially for developers of machine translation systems, computational linguists and language workers. It offers a valuable resource for specialists and students in natural language processing, machine translation, corpus linguistics and computer-assisted translation, and promotes the broader use of comparable corpora in natural language processing and computational linguistics.

This book is the result of a group of researchers from different disciplines asking themselves one question: what does it take to develop a computer interface that listens, talks, and can answer questions in a domain? First, obviously, it takes specialized modules for speech recognition and synthesis, human interaction management (dialogue, input fusion, and multimodal output fusion), basic question understanding, and answer finding. While all modules are researched as independent subfields, this book describes the development of state-of-the-art modules and their integration into a single, working application capable of answering medical (encyclopedic) questions such as "How long is a person with measles contagious?" or "How can I prevent RSI?".The contributions in this book, which grew out of the IMIX project funded by the Netherlands Organisation for Scientific Research, document the development of this system, but also address more general issues in natural language processing, such as the development of multidimensional dialogue systems, the acquisition of taxonomic knowledge from text, answer fusion, sequence processing for domain-specific entity recognition, and syntactic parsing for question answering. Together, they offer an overview of the most important findings and lessons learned in the scope of the IMIX project, making the book of interest to both academic and commercial developers of human-machine interaction systems in Dutch or any other language.Highlights include: integrating multi-modal input fusion in dialogue management (Van Schooten and Op den Akker), state-of-the-art approaches to the extraction of term variants (Van der Plas, Tiedemann, and Fahmi; Tjong Kim Sang, Hofmann, and De Rijke), and multi-modal answer fusion (two chapters by Van Hooijdonk, Bosma, Krahmer, Maes, Theune, and Marsi).Watch the IMIX movie at www.nwo.nl/imix-film.Like IBM's Watson, the IMIX system described in the book gives naturally phrased responses to naturally posed questions. Where Watson can only generate synthetic speech, the IMIX system also recognizes speech. On the other hand, Watson is able to win a television quiz, while the IMIX system is domain-specific, answering only to medical questions."The Netherlands has always been one of the leaders in the general field of Human Language Technology, and IMIX is no exception. It was a very ambitious program, with a remarkably successful performance leading to interesting results. The teams covered a remarkable amount of territory in the general sphere of multimodal  question answering and information delivery, question answering, information extraction and component technologies."Eduard Hovy, USC, USA, Jon Oberlander, University of Edinburgh, Scotland, and Norbert Reithinger, DFKI, Germany

The digital age has had a profound effect on our cultural heritage and the academic research that studies it. Staggering amounts of objects, many of them of a textual nature, are being digitised to make them more readily accessible to both experts and laypersons. Besides a vast potential for more effective and efficient preservation, management, and presentation, digitisation offers opportunities to work with cultural heritage data in ways that were never feasible or even imagined.  To explore and exploit these possibilities, an interdisciplinary approach is needed, bringing together experts from cultural heritage, the social sciences and humanities on the one hand, and information technology on the other. Due to a prevalence of textual data in these domains, language technology has a crucial role to play in this endeavour. Language technology can break through the "Google barrier" by offering the potential to analyse texts at advanced levels, extracting information and knowledge at the level of the humanities or social sciences researcher, who wants to know about the who, what, where, and when, but also the how and the why. At the same time cultural heritage data poses considerable challenges for existing language technology: technology aimed at "generic" language has to face such disparate problems as historical language variation, OCR digitisation errors, and near-extinct academic expertise.  This book is primarily intended for researchers in information technology and language processing who would like to receive a state-of-the-art overview of the whole breadth of the new and vibrant field of language technology for cultural heritage and its associated academic research in the humanities and social sciences. Researchers working in the target domains of cultural heritage, the social sciences and humanities will also find this book useful, as it provides an overview of how language technology can help them with their informationneeds. The book covers applications ranging from pre-processing and data cleaning, to the adaptation and compilation of linguistic resources, to personalisation, narrative analysis, visualisation and retrieval.

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.

The impact of computer systems that can understand natural language will be tremendous. To develop this capability we need to be able to automatically and efficiently analyze large amounts of text. Manually devised rules are not sufficient to provide coverage to handle the complex structure of natural language, necessitating systems that can automatically learn from examples. To handle the flexibility of natural language, it has become standard practice to use statistical models, which assign probabilities for example to the different meanings of a word or the plausibility of grammatical constructions.This book develops a general coarse-to-fine framework for learning and inference in large statistical models for natural language processing.Coarse-to-fine approaches exploit a sequence of models which introduce complexity gradually. At the top of the sequence is a trivial model in which learning and inference are both cheap. Each subsequent model refines the previous one, until a final, full-complexity model is reached. Applications of this framework to syntactic parsing, speech recognition and machine translation are presented, demonstrating the effectiveness of the approach in terms of accuracy and speed. The book is intended for students and researchers interested in statistical approaches to Natural Language Processing. Slav’s work Coarse-to-Fine Natural Language Processing represents a major advance in the area of syntactic parsing, and a great advertisement for the superiority of the machine-learning approach.Eugene Charniak (Brown University)

The past decade has seen a revolution in the field of spoken dialogue systems. As in other areas of Computer Science and Artificial Intelligence, data-driven methods are now being used to drive new methodologies for system development and evaluation. This book is a unique contribution to that ongoing change. A new  methodology for developing spoken dialogue systems is described in detail. The journey starts and ends with human behaviour in interaction, and explores methods for learning from the data, for building simulation environments for training and testing systems, and for evaluating the results. The detailed material covers: Spoken and Multimodal dialogue systems, Wizard-of-Oz data collection, User Simulation methods, Reinforcement Learning, and Evaluation methodologies. The book is a research guide for students and researchers with a background in Computer Science, AI, or Machine Learning. It navigates through a detailed case study in data-driven methods for development and evaluation of spoken dialogue systems. Common challenges associated with this approach are discussed and example solutions are provided. This work provides insights, lessons, and inspiration for future research and development – not only for spoken dialogue systems in particular, but for data-driven approaches to human-machine interaction in general.

Current language technology is dominated by approaches that either enumerate a large set of rules, or are focused on a large amount of manually labelled data. The creation of both is time-consuming and expensive, which is commonly thought to be the reason why automated natural language understanding has still not made its way into “real-life” applications yet. This book sets an ambitious goal: to shift the development of language processing systems to a much more automated setting than previous works. A new approach is defined: what if computers analysed large samples of language data on their own, identifying structural regularities that perform the necessary abstractions and generalisations in order to better understand language in the process?After defining the framework of Structure Discovery and shedding light on the nature and the graphic structure of natural language data, several procedures are described that do exactly this: let the computer discover structures without supervision in order to boost the performance of language technology applications. Here, multilingual documents are sorted by language, word classes are identified, and semantic ambiguities are discovered and resolved without using a dictionary or other explicit human input. The book concludes with an outlook on the possibilities implied by this paradigm and sets the methods in perspective to human computer interaction.The target audience are academics on all levels (undergraduate and graduate students, lecturers and professors) working in the fields of natural language processing and computational linguistics, as well as natural language engineers who are seeking to improve their systems.

This book is the result of a group of researchers from different disciplines asking themselves one question: what does it take to develop a computer interface that listens, talks, and can answer questions in a domain? First, obviously, it takes specialized modules for speech recognition and synthesis, human interaction management (dialogue, input fusion, and multimodal output fusion), basic question understanding, and answer finding. While all modules are researched as independent subfields, this book describes the development of state-of-the-art modules and their integration into a single, working application capable of answering medical (encyclopedic) questions such as "How long is a person with measles contagious?" or "How can I prevent RSI?".The contributions in this book, which grew out of the IMIX project funded by the Netherlands Organisation for Scientific Research, document the development of this system, but also address more general issues in natural language processing, such as the development of multidimensional dialogue systems, the acquisition of taxonomic knowledge from text, answer fusion, sequence processing for domain-specific entity recognition, and syntactic parsing for question answering. Together, they offer an overview of the most important findings and lessons learned in the scope of the IMIX project, making the book of interest to both academic and commercial developers of human-machine interaction systems in Dutch or any other language.Highlights include: integrating multi-modal input fusion in dialogue management (Van Schooten and Op den Akker), state-of-the-art approaches to the extraction of term variants (Van der Plas, Tiedemann, and Fahmi; Tjong Kim Sang, Hofmann, and De Rijke), and multi-modal answer fusion (two chapters by Van Hooijdonk, Bosma, Krahmer, Maes, Theune, and Marsi).Watch the IMIX movie at www.nwo.nl/imix-film.Like IBM's Watson, the IMIX system described in the book gives naturally phrased responses to naturally posed questions. Where Watson can only generate synthetic speech, the IMIX system also recognizes speech. On the other hand, Watson is able to win a television quiz, while the IMIX system is domain-specific, answering only to medical questions."The Netherlands has always been one of the leaders in the general field of Human Language Technology, and IMIX is no exception. It was a very ambitious program, with a remarkably successful performance leading to interesting results. The teams covered a remarkable amount of territory in the general sphere of multimodal  question answering and information delivery, question answering, information extraction and component technologies."Eduard Hovy, USC, USA, Jon Oberlander, University of Edinburgh, Scotland, and Norbert Reithinger, DFKI, Germany

The digital age has had a profound effect on our cultural heritage and the academic research that studies it. Staggering amounts of objects, many of them of a textual nature, are being digitised to make them more readily accessible to both experts and laypersons. Besides a vast potential for more effective and efficient preservation, management, and presentation, digitisation offers opportunities to work with cultural heritage data in ways that were never feasible or even imagined.  To explore and exploit these possibilities, an interdisciplinary approach is needed, bringing together experts from cultural heritage, the social sciences and humanities on the one hand, and information technology on the other. Due to a prevalence of textual data in these domains, language technology has a crucial role to play in this endeavour. Language technology can break through the "Google barrier" by offering the potential to analyse texts at advanced levels, extracting information and knowledge at the level of the humanities or social sciences researcher, who wants to know about the who, what, where, and when, but also the how and the why. At the same time cultural heritage data poses considerable challenges for existing language technology: technology aimed at "generic" language has to face such disparate problems as historical language variation, OCR digitisation errors, and near-extinct academic expertise.  This book is primarily intended for researchers in information technology and language processing who would like to receive a state-of-the-art overview of the whole breadth of the new and vibrant field of language technology for cultural heritage and its associated academic research in the humanities and social sciences. Researchers working in the target domains of cultural heritage, the social sciences and humanities will also find this book useful, as it provides an overview of how language technology can help them with their informationneeds. The book covers applications ranging from pre-processing and data cleaning, to the adaptation and compilation of linguistic resources, to personalisation, narrative analysis, visualisation and retrieval.

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.

Information extraction (IE) and text summarization (TS) are powerful technologies for finding relevant pieces of information in text and presenting them to the user in condensed form.

This book provides an overview of more than a decade of joint R&D efforts in the Low Countries on HLT for Dutch. It details concrete results (resources and tools for Dutch) achieved that have now become available for both academia and industry worldwide.

This book explores recent advances in the integration of ontologies and lexical resources, including questions such as building the required infrastructure (e.g., the Semantic Web) and different formalisms, methods and platforms for eliciting, analyzing and encoding knowledge contents (e.g., multimedia, emotions, events, etc.).

Discusses some of the theoretical and practical developments in the areas involved, including computational models for language tasks, tools and resources that helps to approximate the linguistic environment available to children during acquisition, and discussions of challenging aspects of language that children have to master.

Collaboratively Constructed Language Resources (CCLRs) such as Wikipedia, Wiktionary, Linked Open Data, and various resources developed using crowdsourcing techniques such as Games with a Purpose and Mechanical Turk have substantially contributed to the research in natural language processing (NLP). Various NLP tasks utilize such resources to substitute for or supplement conventional lexical semantic resources and linguistically annotated corpora. These resources also provide an extensive body of texts from which valuable knowledge is mined. There are an increasing number of community efforts to link and maintain multiple linguistic resources. This book aims offers comprehensive coverage of CCLR-related topics, including their construction, utilization in NLP tasks, and interlinkage and management. Various Bachelor/Master/Ph.D. programs in natural language processing, computational linguistics, and knowledge discovery can use this book both as the main text and as a supplementary reading. The book also provides a valuable reference guide for researchers and professionals for the above topics.

The impact of computer systems that can understand natural language will be tremendous. To develop this capability we need to be able to automatically and efficiently analyze large amounts of text. Manually devised rules are not sufficient to provide coverage to handle the complex structure of natural language, necessitating systems that can automatically learn from examples. To handle the flexibility of natural language, it has become standard practice to use statistical models, which assign probabilities for example to the different meanings of a word or the plausibility of grammatical constructions.This book develops a general coarse-to-fine framework for learning and inference in large statistical models for natural language processing.Coarse-to-fine approaches exploit a sequence of models which introduce complexity gradually. At the top of the sequence is a trivial model in which learning and inference are both cheap. Each subsequent model refines the previous one, until a final, full-complexity model is reached. Applications of this framework to syntactic parsing, speech recognition and machine translation are presented, demonstrating the effectiveness of the approach in terms of accuracy and speed. The book is intended for students and researchers interested in statistical approaches to Natural Language Processing. Slav’s work Coarse-to-Fine Natural Language Processing represents a major advance in the area of syntactic parsing, and a great advertisement for the superiority of the machine-learning approach.Eugene Charniak (Brown University)

Questions related to language acquisition have been of interest for many centuries, as children seem to acquire a sophisticated capacity for processing language with apparent ease, in the face of ambiguity, noise and uncertainty. However, with recent advances in technology and cognitive-related research it is now possible to conduct large-scale computational investigations of these issuesThe book discusses some of the latest theoretical and practical developments in the areas involved, including computational models for language tasks, tools and resources that help to approximate the linguistic environment available to children during acquisition, and discussions of challenging aspects of language that children have to master. This is a much-needed collection that provides a cross-section of recent multidisciplinary research on the computational modeling of language acquisition. It is targeted at anyone interested in the relevance of computational techniques for understanding language acquisition. Readers of this book will be introduced to some of the latest approaches to these tasks including:* Models of acquisition of various types of linguistic information (from words to syntax and semantics) and their relevance to research on human language acquisition * Analysis of linguistic and contextual factors that influence acquisition * Resources and tools for investigating these tasksEach chapter is presented in a self-contained manner, providing a detailed description of the relevant aspects related to research on language acquisition, and includes illustrations and tables to complement these in-depth discussions. Though there are no formal prerequisites, some familiarity with the basic concepts of human and computational language acquisition is beneficial.

The book provides an overview of more than a decade of joint R&D efforts in the Low Countries on HLT for Dutch. It not only presents the state of the art of HLT for Dutch in the areas covered, but, even more importantly, a description of the resources (data and tools) for Dutch that have been created  are now  available for both academia and industry worldwide. The contributions cover many areas of human language technology (for Dutch): corpus collection (including IPR issues) and building (in particular one corpus aiming at a collection of 500M word tokens), lexicology, anaphora resolution, a semantic network, parsing technology, speech recognition, machine translation, text (summaries) generation, web mining, information extraction, and text to speech to name the most important ones.The book also shows how a medium-sized language community (spanning two territories) can create a digital language infrastructure (resources, tools, etc.) as a basis for subsequent R&D. At the same time, it bundles contributions of almost all the HLT research groups in Flanders and the Netherlands, hence offers a view of their recent research activities.Targeted readers are mainly researchers in human language technology, in particular those focusing on Dutch. It concerns researchers active in larger networks such as the CLARIN, META-NET, FLaReNet and participating in conferences such as ACL, EACL, NAACL, COLING, RANLP, CICling, LREC, CLIN and DIR ( both in the Low Countries), InterSpeech, ASRU, ICASSP, ISCA, EUSIPCO, CLEF, TREC, etc. In addition, some chapters are interesting for human language technology  policy makers and even for science policy makers in general.

Information extraction (IE) and text summarization (TS) are powerful technologies for finding relevant pieces of information in text and presenting them to the user in condensed form. The ongoing information explosion makes IE and TS critical for successful functioning within the information society. These technologies face particular challenges due to the inherent multi-source nature of the information explosion.  The technologies must now handle not isolated texts or individual narratives, but rather large-scale repositories and streams---in general, in multiple languages---containing a multiplicity of perspectives, opinions, or commentaries on particular topics, entities or events.  There is thus a need to adapt existing techniques and develop new ones to deal with these challenges. This volume contains a selection of papers that present a variety of methodologies for content identification and extraction, as well as for content fusion and regeneration. The chapters cover various aspects of the challenges, depending on the nature of the information sought---names vs. events,--- and the nature of the sources---news streams vs. image captions vs. scientific research papers, etc. This volume aims to offer a broad and representative sample of studies from this very active research field.

This book explores recent advances in the integration of ontologies and lexical resources, including questions such as building the required infrastructure (e.g., the Semantic Web) and different formalisms, methods and platforms for eliciting, analyzing and encoding knowledge contents (e.g., multimedia, emotions, events, etc.).

Collaboratively Constructed Language Resources (CCLRs) such as Wikipedia, Wiktionary, Linked Open Data, and various resources developed using crowdsourcing techniques such as Games with a Purpose and Mechanical Turk have substantially contributed to the research in natural language processing (NLP).