This book builds on decades of research and provides contemporary theoretical foundations for practical applications to intelligent technologies and advances in artificial intelligence (AI). Reflecting the growing realization that computational models of human reasoning and interactions can be improved by integrating heterogeneous information resources and AI techniques, its ultimate goal is to promote integrated computational approaches to intelligent computerized systems. The book covers a range of interrelated topics, in particular, computational reasoning, language, syntax, semantics, memory, and context information. The respective chapters use and develop logically oriented methods and techniques, and the topics selected are from those areas of logic that contribute to AI and provide its mathematical foundations. The intended readership includes researchers working in the areas of traditional logical foundations, and on new approaches to intelligent computational systems.

This book constitutes the refereed proceedings of the 14th International Conference on Formal Grammar 2009, held in Bordeaux, France, in July 2009.
The 13 revised full papers presented, including two invited talks, were carefully reviewed and selected from 26 submissions. These articles in this book give an overview of new and original research on formal grammar, mathematical linguistics and the application of formal and mathematical methods to the study of natural language.

This book provides a timely and comprehensive overview of current theories and methods in fuzzy logic, as well as relevant applications in a variety of fields of science and technology. Dedicated to Lotfi A. Zadeh on his one year death anniversary, the book goes beyond a pure commemorative text. Yet, it offers a fresh perspective on a number of relevant topics, such as computing with words, theory of perceptions, possibility theory, and decision-making in a fuzzy environment. Written by Zadeh's closest colleagues and friends, the different chapters are intended both as a timely reference guide and a source of inspiration for scientists, developers and researchers who have been dealing with fuzzy sets or would like to learn more about their potential for their future research.

Opportunity and Curiosity find similar rocks on Mars. One can generally understand this statement if one knows that Opportunity and Curiosity are instances of the class of Mars rovers, and recognizes that, as signalled by the word on, rocks are located on Mars. Two mental operations contribute to understanding: recognize how entities/concepts mentioned in a text interact and recall already known facts (which often themselves consist of relations between entities/concepts). Concept interactions one identifies in the text can be added to the repository of known facts, and aid the processing of future texts. The amassed knowledge can assist many advanced language-processing tasks, including summarization, question answering and machine translation. Semantic relations are the connections we perceive between things which interact. The book explores two, now intertwined, threads in semantic relations: how they are expressed in texts and what role they play in knowledge repositories. A historical perspective takes us back more than 2000 years to their beginnings, and then to developments much closer to our time: various attempts at producing lists of semantic relations, necessary and sufficient to express the interaction between entities/concepts. A look at relations outside context, then in general texts, and then in texts in specialized domains, has gradually brought new insights, and led to essential adjustments in how the relations are seen. At the same time, datasets which encompass these phenomena have become available. They started small, then grew somewhat, then became truly large. The large resources are inevitably noisy because they are constructed automatically. The available corpora-to be analyzed, or used to gather relational evidence-have also grown, and some systems now operate at the Web scale. The learning of semantic relations has proceeded in parallel, in adherence to supervised, unsupervised or distantly supervised paradigms. Detailed analyses of annotated datasets in supervised learning have granted insights useful in developing unsupervised and distantly supervised methods. These in turn have contributed to the understanding of what relations are and how to find them, and that has led to methods scalable to Web-sized textual data. The size and redundancy of information in very large corpora, which at first seemed problematic, have been harnessed to improve the process of relation extraction/learning. The newest technology, deep learning, supplies innovative and surprising solutions to a variety of problems in relation learning. This book aims to paint a big picture and to offer interesting details.

Embeddings have undoubtedly been one of the most influential research areas in Natural Language Processing (NLP). Encoding information into a low-dimensional vector representation, which is easily integrable in modern machine learning models, has played a central role in the development of NLP. Embedding techniques initially focused on words, but the attention soon started to shift to other forms: from graph structures, such as knowledge bases, to other types of textual content, such as sentences and documents. This book provides a high-level synthesis of the main embedding techniques in NLP, in the broad sense. The book starts by explaining conventional word vector space models and word embeddings (e.g., Word2Vec and GloVe) and then moves to other types of embeddings, such as word sense, sentence and document, and graph embeddings. The book also provides an overview of recent developments in contextualized representations (e.g., ELMo and BERT) and explains their potential in NLP. Throughout the book, the reader can find both essential information for understanding a certain topic from scratch and a broad overview of the most successful techniques developed in the literature.

Focusing on methodologies, applications and challenges of textual data analysis and related fields, this book gathers selected and peer-reviewed contributions presented at the 14th International Conference on Statistical Analysis of Textual Data (JADT 2018), held in Rome, Italy, on June 12-15, 2018. Statistical analysis of textual data is a multidisciplinary field of research that has been mainly fostered by statistics, linguistics, mathematics and computer science. The respective sections of the book focus on techniques, methods and models for text analytics, dictionaries and specific languages, multilingual text analysis, and the applications of text analytics. The interdisciplinary contributions cover topics including text mining, text analytics, network text analysis, information extraction, sentiment analysis, web mining, social media analysis, corpus and quantitative linguistics, statistical and computational methods, and textual data in sociology, psychology, politics, law and marketing.

This book focuses mainly on logical approaches to computational linguistics, but also discusses integrations with other approaches, presenting both classic and newly emerging theories and applications.Decades of research on theoretical work and practical applications have demonstrated that computational linguistics is a distinctively interdisciplinary area. There is convincing evidence that computational approaches to linguistics can benefit from research on the nature of human language, including from the perspective of its evolution. This book addresses various topics in computational theories of human language, covering grammar, syntax, and semantics. The common thread running through the research presented is the role of computer science, mathematical logic and other subjects of mathematics in computational linguistics and natural language processing (NLP). Promoting intelligent approaches to artificial intelligence (AI) and NLP, the book is intended for researchers and graduate students in the field.

This open access book provides an overview of the recent advances in representation learning theory, algorithms and applications for natural language processing (NLP). It is divided into three parts. Part I presents the representation learning techniques for multiple language entries, including words, phrases, sentences and documents. Part II then introduces the representation techniques for those objects that are closely related to NLP, including entity-based world knowledge, sememe-based linguistic knowledge, networks, and cross-modal entries. Lastly, Part III provides open resource tools for representation learning techniques, and discusses the remaining challenges and future research directions. The theories and algorithms of representation learning presented can also benefit other related domains such as machine learning, social network analysis, semantic Web, information retrieval, data mining and computational biology. This book is intended for advanced undergraduate and graduate students, post-doctoral fellows, researchers, lecturers, and industrial engineers, as well as anyone interested in representation learning and natural language processing.

First published a decade ago, "CJKV Information Processing" quickly became the unsurpassed source of information on processing text in Chinese, Japanese, Korean, and Vietnamese. The book has now been thoroughly updated to provide web and application developers with the latest techniques and tools for disseminating information directly to audiences in East Asia. This new second edition reflects the considerable impact that Unicode, XML, OpenType, and newer operating systems such as Windows XP, Vista, Mac OS X, and Linux have had on East Asian text processing in recent years. Written by its original author, Ken Lunde, a Senior Computer Scientist in CJKV Type Development at Adobe Systems, this book will help you: learn about CJKV writing systems and scripts, and their transliteration methods; explore recent trends and developments in character sets and encodings, particularly Unicode; examine the world of typography, specifically how CJKV text is laid out on a page; learn information processing techniques, such as code conversion algorithms and how to apply them using different programming languages; process CJKV text using different platforms, text editors, and word processors; become more informed about CJKV dictionaries, dictionary software, and machine translation software and services; and, manage CJKV content and presentation when publishing in print or for the Web And much more. Internationalizing and localizing applications is paramount in today's global market - especially for audiences in East Asia, the fastest-growing segment of the computing world. "CJKV Information Processing" will help you understand how to develop web and other applications effectively in a field that many find difficult to master.

This book introduces a novel type of expert finder system that can determine the knowledge that specific users within a community hold, using explicit and implicit data sources to do so. Further, it details how this is accomplished by combining granular computing, natural language processing and a set of metrics that it introduces to measure and compare candidates' suitability. The book describes profiling techniques that can be used to assess knowledge requirements on the basis of a given problem statement or question, so as to ensure that only the most suitable candidates are recommended. The book brings together findings from natural language processing, artificial intelligence and big data, which it subsequently applies to the context of expert finder systems. Accordingly, it will appeal to researchers, developers and innovators alike.

This book focuses on information literacy for the younger generation of learners and library readers. It is divided into four sections: 1. Information Literacy for Life; 2. Searching Strategies, Disciplines and Special Topics; 3. Information Literacy Tools for Evaluating and Utilizing Resources; 4. Assessment of Learning Outcomes. Written by librarians with wide experience in research and services, and a strong academic background in disciplines such as the humanities, social sciences, information technology, and library science, this valuable reference resource combines both theory and practice. In today's ever-changing era of information, it offers students of library and information studies insights into information literacy as well as learning tips they can use for life.

This volume presents several machine intelligence technologies, developed over recent decades, and illustrates how they can be combined in application. One application, the detection of dementia from patterns in speech, is used throughout to illustrate these combinations. This application is a classic stationary pattern detection task, so readers may easily see how these combinations can be applied to other similar tasks. The expositions of the methods are supported by the basic theory they rest upon, and their application is clearly illustrated. The book's goal is to allow readers to select one or more of these methods to quickly apply to their own tasks. Includes a variety of machine intelligent technologies and illustrates how they can work together Shows evolutionary feature subset selection combined with support vector machines and multiple classifiers combined Includes a running case study on intelligent processing relating to Alzheimer's / dementia detection, in addition to several applications of the machine hybrid algorithms

The general focus of this book is on multimodal communication, which captures the temporal patterns of behavior in various dialogue settings. After an overview of current theoretical models of verbal and nonverbal communication cues, it presents studies on a range of related topics: paraverbal behavior patterns in the classroom setting; a proposed optimal methodology for conversational analysis; a study of time and mood at work; an experiment on the dynamics of multimodal interaction from the observer's perspective; formal cues of uncertainty in conversation; how machines can know we understand them; and detecting topic changes using neural network techniques. A joint work bringing together psychologists, communication scientists, information scientists and linguists, the book will be of interest to those working on a wide range of applications from industry to home, and from health to security, with the main goals of revealing, embedding and implementing a rich spectrum of information on human behavior.

The research described in this book shows that conversation analysis can effectively model dialogue. Specifically, this work shows that the multidisciplinary field of communicative ICALL may greatly benefit from including Conversation Analysis. As a consequence, this research makes several contributions to the related research disciplines, such as conversation analysis, second-language acquisition, computer-mediated communication, artificial intelligence, and dialogue systems. The book will be of value for researchers and engineers in the areas of computational linguistics, intelligent assistants, and conversational interfaces.

This book provides information on digital audio watermarking, its applications, and its evaluation for copyright protection of audio signals - both basic and advanced. The author covers various advanced digital audio watermarking algorithms that can be used for copyright protection of audio signals. These algorithms are implemented using hybridization of advanced signal processing transforms such as fast discrete curvelet transform (FDCuT), redundant discrete wavelet transform (RDWT), and another signal processing transform such as discrete cosine transform (DCT). In these algorithms, Arnold scrambling is used to enhance the security of the watermark logo. This book is divided in to three portions: basic audio watermarking and its classification, audio watermarking algorithms, and audio watermarking algorithms using advance signal transforms. The book also covers optimization based audio watermarking. Describes basic of digital audio watermarking and its applications, including evaluation parameters for digital audio watermarking algorithms; Provides audio watermarking algorithms using advanced signal transformations; Provides optimization based audio watermarking algorithms.

This book constitutes the refereed proceedings of the 16th International Conference of the Pacific Association for Computational Linguistics, PACLING 2019, held in Hanoi, Vietnam, in October 2019. The 28 full papers and 14 short papers presented were carefully reviewed and selected from 70 submissions. The papers are organized in topical sections on text summarization; relation and word embedding; machine translation; text classification; web analyzing; question and answering, dialog analyzing; speech and emotion analyzing; parsing and segmentation; information extraction; and grammar error and plagiarism detection.

This book explains speech enhancement in the Fractional Fourier Transform (FRFT) domain and investigates the use of different FRFT algorithms in both single channel and multi-channel enhancement systems, which has proven to be an ideal time frequency analysis tool in many speech signal processing applications. The authors discuss the complexities involved in the highly non- stationary signal processing and the concepts of FRFT for speech enhancement applications. The book explains the fundamentals of FRFT as well as its implementation in speech enhancement. Theories of different FRFT methods are also discussed. The book lets readers understand the new fractional domains to prepare them to develop new algorithms. A comprehensive literature survey regarding the topic is also made available to the reader.

Language, apart from its cultural and social dimension, has a scientific side that is connected not only to the study of 'grammar' in a more or less traditional sense, but also to disciplines like mathematics, physics, chemistry and biology. This book explores developments in linguistic theory, looking in particular at the theory of generative grammar from the perspective of the natural sciences. It highlights the complex and dynamic nature of language, suggesting that a comprehensive and full understanding of such a species-specific property will only be achieved through interdisciplinary work.

Data-driven experimental analysis has become the main evaluation tool of Natural Language Processing (NLP) algorithms. In fact, in the last decade, it has become rare to see an NLP paper, particularly one that proposes a new algorithm, that does not include extensive experimental analysis, and the number of involved tasks, datasets, domains, and languages is constantly growing. This emphasis on empirical results highlights the role of statistical significance testing in NLP research: If we, as a community, rely on empirical evaluation to validate our hypotheses and reveal the correct language processing mechanisms, we better be sure that our results are not coincidental. The goal of this book is to discuss the main aspects of statistical significance testing in NLP. Our guiding assumption throughout the book is that the basic question NLP researchers and engineers deal with is whether or not one algorithm can be considered better than another one. This question drives the field forward as it allows the constant progress of developing better technology for language processing challenges. In practice, researchers and engineers would like to draw the right conclusion from a limited set of experiments, and this conclusion should hold for other experiments with datasets they do not have at their disposal or that they cannot perform due to limited time and resources. The book hence discusses the opportunities and challenges in using statistical significance testing in NLP, from the point of view of experimental comparison between two algorithms. We cover topics such as choosing an appropriate significance test for the major NLP tasks, dealing with the unique aspects of significance testing for non-convex deep neural networks, accounting for a large number of comparisons between two NLP algorithms in a statistically valid manner (multiple hypothesis testing), and, finally, the unique challenges yielded by the nature of the data and practices of the field.

Il volume presenta uno studio linguistico-testuale di un corpus di post di blog diaristici. L'analisi proposta si colloca all'intersezione di due indirizzi di riflessione, quello testuale e quello piu prettamente linguistico. Nell'ambito del primo il diario on-line viene studiato nelle sue peculiarita testuali e comunicative come genere di discorso all'interno di tre insiemi: generi autobiografici, generi della CMC e testi poco vincolanti. Nell'ambito del secondo viene esaminata la presenza nel corpus di una serie di tratti morfo-sintattici con l'obiettivo di poter qualificare i diari on-line in termini di distanza/vicinanza rispetto alla norma dell'italiano standard. Segue l'analisi di una serie di tratti sintattici tipici del parlato volta a scoprire in che misura i testi del corpus esaminato risultino orientati verso l'oralita.

In recent years, online social networking has revolutionized interpersonal communication. The newer research on language analysis in social media has been increasingly focusing on the latter's impact on our daily lives, both on a personal and a professional level. Natural language processing (NLP) is one of the most promising avenues for social media data processing. It is a scientific challenge to develop powerful methods and algorithms that extract relevant information from a large volume of data coming from multiple sources and languages in various formats or in free form. This book will discuss the challenges in analyzing social media texts in contrast with traditional documents. Research methods in information extraction, automatic categorization and clustering, automatic summarization and indexing, and statistical machine translation need to be adapted to a new kind of data. This book reviews the current research on NLP tools and methods for processing the non-traditional information from social media data that is available in large amounts, and it shows how innovative NLP approaches can integrate appropriate linguistic information in various fields such as social media monitoring, health care, and business intelligence. The book further covers the existing evaluation metrics for NLP and social media applications and the new efforts in evaluation campaigns or shared tasks on new datasets collected from social media. Such tasks are organized by the Association for Computational Linguistics (such as SemEval tasks), the National Institute of Standards and Technology via the Text REtrieval Conference (TREC) and the Text Analysis Conference (TAC), or the Conference and Labs of the Evaluation Forum (CLEF). In this third edition of the book, the authors added information about recent progress in NLP for social media applications, including more about the modern techniques provided by deep neural networks (DNNs) for modeling language and analyzing social media data.

This book constitutes the proceedings of the 14th International Conference on Computational Processing of the Portuguese Language, PROPOR 2020, held in Evora, Portugal, in March 2020. The 36 full papers presented together with 5 short papers were carefully reviewed and selected from 70 submissions. They are grouped in topical sections on speech processing; resources and evaluation; natural language processing applications; semantics; natural language processing tasks; and multilinguality.

Text production has many applications. It is used, for instance, to generate dialogue turns from dialogue moves, verbalise the content of knowledge bases, or generate English sentences from rich linguistic representations, such as dependency trees or abstract meaning representations. Text production is also at work in text-to-text transformations such as sentence compression, sentence fusion, paraphrasing, sentence (or text) simplification, and text summarisation. This book offers an overview of the fundamentals of neural models for text production. In particular, we elaborate on three main aspects of neural approaches to text production: how sequential decoders learn to generate adequate text, how encoders learn to produce better input representations, and how neural generators account for task-specific objectives. Indeed, each text-production task raises a slightly different challenge (e.g, how to take the dialogue context into account when producing a dialogue turn, how to detect and merge relevant information when summarising a text, or how to produce a well-formed text that correctly captures the information contained in some input data in the case of data-to-text generation). We outline the constraints specific to some of these tasks and examine how existing neural models account for them. More generally, this book considers text-to-text, meaning-to-text, and data-to-text transformations. It aims to provide the audience with a basic knowledge of neural approaches to text production and a roadmap to get them started with the related work. The book is mainly targeted at researchers, graduate students, and industrials interested in text production from different forms of inputs.

The question of what types of data and evidence can be used is one of the most important topics in linguistics. This book is the first to comprehensively present the methodological problems associated with linguistic data and evidence. Its originality is twofold. First, the authors' approach accounts for a series of unexplained characteristics of linguistic theorising: the uncertainty and diversity of data, the role of evidence in the evaluation of hypotheses, and the problem solving strategies, as well as the emergence and resolution of inconsistencies. Second, the findings are obtained by the application of a new model of plausible argumentation which is also of relevance from a general argumentation theoretical point of view. All concepts and theses are systematically introduced and illustrated by a number of examples from different linguistic theories, and a detailed case-study section shows how the proposed model can be applied to specific linguistic problems.

Meaning is a fundamental concept in Natural Language Processing (NLP), in the tasks of both Natural Language Understanding (NLU) and Natural Language Generation (NLG). This is because the aims of these fields are to build systems that understand what people mean when they speak or write, and that can produce linguistic strings that successfully express to people the intended content. In order for NLP to scale beyond partial, task-specific solutions, researchers in these fields must be informed by what is known about how humans use language to express and understand communicative intents. The purpose of this book is to present a selection of useful information about semantics and pragmatics, as understood in linguistics, in a way that's accessible to and useful for NLP practitioners with minimal (or even no) prior training in linguistics.