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.

Now in its second edition, this volume provides an up to date, accessible, yet authoritative introduction to feedback on second language writing for upper undergraduate and postgraduate students, teachers and researchers in TESOL, applied linguistics, composition studies and English for academic purposes (EAP). Chapters written by leading experts emphasise the potential that feedback has for helping to create a supportive teaching environment, for conveying and modelling ideas about good writing, for developing the ways students talk about writing, and for mediating the relationship between students' wider cultural and social worlds and their growing familiarity with new literacy practices. In addition to updated chapters from the first edition, this edition includes new chapters which focus on new and developing areas of feedback research including student engagement and participation with feedback, the links between SLA and feedback research, automated computer feedback and the use by students of internet resources and social media as feedback resources.

What is the lexicon, what does it contain, and how is it structured? What principles determine the functioning of the lexicon as a component of natural language grammar? What role does lexical information play in linguistic theory? This accessible introduction aims to answer these questions, and explores the relation of the lexicon to grammar as a whole. It includes a critical overview of major theoretical frameworks, and puts forward a unified treatment of lexical structure and design. The text can be used for introductory and advanced courses, and for courses that touch upon different aspects of the lexicon, such as lexical semantics, lexicography, syntax, general linguistics, computational lexicology and ontology design. The book provides students with a set of tools which will enable them to work with lexical data for all kinds of purposes, including an abundance of exercises and in-class activities designed to ensure that students are actively engaged with the content and effectively acquire the necessary knowledge and skills they need.

This book integrates current advances in biology, economics of information and linguistics research through applications using agent-based modeling and social network analysis to develop scenarios of communication and language emergence in the social aspects of biological communications. The book presents a model of communication emergence that can be applied both to human and non-human living organism networks. The model is based on economic concepts and individual behavior fundamental for the study of trust and reputation networks in social science, particularly in economics; it is also based on the theory of the emergence of norms and historical path dependence that has been influential in institutional economics. Also included are mathematical models and code for agent-based models to explore various scenarios of language evolution, as well as a computer application that explores language and communication in biological versus social organisms, and the emergence of various meanings and grammars in human networks. Emergence of Communication in Socio-Biological Networks offers both a completely novel approach to communication emergence and language evolution and provides a path for the reader to explore various scenarios of language and communication that are not constrained to the human networks alone. By illustrating how computational social science and the complex systems approach can incorporate multiple disciplines and offer an integrated theory-model approach to the evolution of language, the book will be of interest to researchers working with computational linguistics, mathematical linguistics, and complex systems.

This book presents multibiometric watermarking techniques for security of biometric data. This book also covers transform domain multibiometric watermarking techniques and their advantages and limitations. The authors have developed novel watermarking techniques with a combination of Compressive Sensing (CS) theory for the security of biometric data at the system database of the biometric system. The authors show how these techniques offer higher robustness, authenticity, better imperceptibility, increased payload capacity, and secure biometric watermarks. They show how to use the CS theory for the security of biometric watermarks before embedding into the host biometric data. The suggested methods may find potential applications in the security of biometric data at various banking applications, access control of laboratories, nuclear power stations, military base, and airports.

The majority of natural language processing (NLP) is English language processing, and while there is good language technology support for (standard varieties of) English, support for Albanian, Burmese, or Cebuano--and most other languages--remains limited. Being able to bridge this digital divide is important for scientific and democratic reasons but also represents an enormous growth potential. A key challenge for this to happen is learning to align basic meaning-bearing units of different languages. In this book, the authors survey and discuss recent and historical work on supervised and unsupervised learning of such alignments. Specifically, the book focuses on so-called cross-lingual word embeddings. The survey is intended to be systematic, using consistent notation and putting the available methods on comparable form, making it easy to compare wildly different approaches. In so doing, the authors establish previously unreported relations between these methods and are able to present a fast-growing literature in a very compact way. Furthermore, the authors discuss how best to evaluate cross-lingual word embedding methods and survey the resources available for students and researchers interested in this topic.

This book introduces audio watermarking methods in transform domain based on matrix decomposition for copyright protection. Chapter 1 discusses the application and properties of digital watermarking. Chapter 2 proposes a blind lifting wavelet transform (LWT) based watermarking method using fast Walsh Hadamard transform (FWHT) and singular value decomposition (SVD) for audio copyright protection. Chapter 3 presents a blind audio watermarking method based on LWT and QR decomposition (QRD) for audio copyright protection. Chapter 4 introduces an audio watermarking algorithm based on FWHT and LU decomposition (LUD). Chapter 5 proposes an audio watermarking method based on LWT and Schur decomposition (SD). Chapter 6 explains in details on the challenges and future trends of audio watermarking in various application areas. Introduces audio watermarking methods for copyright protection and ownership protection; Describes watermarking methods with encryption and decryption that provide excellent performance in terms of imperceptibility, robustness, and data payload; Discusses in details on the challenges and future research direction of audio watermarking in various application areas.

Natural language processing (NLP) went through a profound transformation in the mid-1980s when it shifted to make heavy use of corpora and data-driven techniques to analyze language. Since then, the use of statistical techniques in NLP has evolved in several ways. One such example of evolution took place in the late 1990s or early 2000s, when full-fledged Bayesian machinery was introduced to NLP. This Bayesian approach to NLP has come to accommodate various shortcomings in the frequentist approach and to enrich it, especially in the unsupervised setting, where statistical learning is done without target prediction examples. In this book, we cover the methods and algorithms that are needed to fluently read Bayesian learning papers in NLP and to do research in the area. These methods and algorithms are partially borrowed from both machine learning and statistics and are partially developed "in-house" in NLP. We cover inference techniques such as Markov chain Monte Carlo sampling and variational inference, Bayesian estimation, and nonparametric modeling. In response to rapid changes in the field, this second edition of the book includes a new chapter on representation learning and neural networks in the Bayesian context. We also cover fundamental concepts in Bayesian statistics such as prior distributions, conjugacy, and generative modeling. Finally, we review some of the fundamental modeling techniques in NLP, such as grammar modeling, neural networks and representation learning, and their use with Bayesian analysis.

The objective of this monograph is to improve the performance of the sentiment analysis model by incorporating the semantic, syntactic and common-sense knowledge. This book proposes a novel semantic concept extraction approach that uses dependency relations between words to extract the features from the text. Proposed approach combines the semantic and common-sense knowledge for the better understanding of the text. In addition, the book aims to extract prominent features from the unstructured text by eliminating the noisy, irrelevant and redundant features. Readers will also discover a proposed method for efficient dimensionality reduction to alleviate the data sparseness problem being faced by machine learning model. Authors pay attention to the four main findings of the book : -Performance of the sentiment analysis can be improved by reducing the redundancy among the features. Experimental results show that minimum Redundancy Maximum Relevance (mRMR) feature selection technique improves the performance of the sentiment analysis by eliminating the redundant features. - Boolean Multinomial Naive Bayes (BMNB) machine learning algorithm with mRMR feature selection technique performs better than Support Vector Machine (SVM) classifier for sentiment analysis. - The problem of data sparseness is alleviated by semantic clustering of features, which in turn improves the performance of the sentiment analysis. - Semantic relations among the words in the text have useful cues for sentiment analysis. Common-sense knowledge in form of ConceptNet ontology acquires knowledge, which provides a better understanding of the text that improves the performance of the sentiment analysis.

This book constitutes the refereed proceedings of the 14th China Workshop on Machine Translation, CWMT 2018, held in Wuyishan, China, in October 2018. The 9 papers presented in this volume were carefully reviewed and selected from 17 submissions and focus on all aspects of machine translation, including preprocessing, neural machine translation models, hybrid model, evaluation method, and post-editing.

This book describes effective methods for automatically analyzing a sentence, based on the syntactic and semantic characteristics of the elements that form it. To tackle ambiguities, the authors use selectional preferences (SP), which measure how well two words fit together semantically in a sentence. Today, many disciplines require automatic text analysis based on the syntactic and semantic characteristics of language and as such several techniques for parsing sentences have been proposed. Which is better? In this book the authors begin with simple heuristics before moving on to more complex methods that identify nouns and verbs and then aggregate modifiers, and lastly discuss methods that can handle complex subordinate and relative clauses. During this process, several ambiguities arise. SP are commonly determined on the basis of the association between a pair of words. However, in many cases, SP depend on more words. For example, something (such as grass) may be edible, depending on who is eating it (a cow?). Moreover, things such as popcorn are usually eaten at the movies, and not in a restaurant. The authors deal with these phenomena from different points of view.

This book re-examines the notion of word associations, more precisely collocations. It attempts to come to a potentially more generally applicable definition of collocation and how to best extract, identify and measure collocations. The book highlights the role played by (i) automatic linguistic annotation (part-of-speech tagging, syntactic parsing, etc.), (ii) using semantic criteria to facilitate the identification of collocations, (iii) multi-word structured, instead of the widespread assumption of bipartite collocational structures, for capturing the intricacies of the phenomenon of syntagmatic attraction, (iv) considering collocation and valency as near neighbours in the lexis-grammar continuum and (v) the mathematical properties of statistical association measures in the automatic extraction of collocations from corpora. This book is an ideal guide to the use of statistics in collocation analysis and lexicography, as well as a practical text to the development of skills in the application of computational lexicography. Lexical Collocation Analysis: Advances and Applications begins with a proposal for integrating both collocational and valency phenomena within the overarching theoretical framework of construction grammar. Next the book makes the case for integrating advances in syntactic parsing and in collocational analysis. Chapter 3 offers an innovative look at complementing corpus data and dictionaries in the identification of specific types of collocations consisting of restricted predicate-argument combinations. This strategy complements corpus collocational data with network analysis techniques applied to dictionary entries. Chapter 4 explains the potential of collocational graphs and networks both as a visualization tool and as an analytical technique. Chapter 5 introduces MERGE (Multi-word Expressions from the Recursive Grouping of Elements), a data-driven approach to the identification and extraction of multi-word expressions from corpora. Finally the book concludes with an analysis and evaluation of factors influencing the performance of collocation extraction methods in parsed corpora.

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 commercial and 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 constitutes the thoroughly refereed proceedings of the Eleventh International Symposium on Natural Language Processing (SNLP-2016), held in Phranakhon Si Ayutthaya, Thailand on February 10-12, 2016. The SNLP promotes research in natural language processing and related fields, and provides a unique opportunity for researchers, professionals and practitioners to discuss various current and advanced issues of interest in NLP. The 2016 symposium was expanded to include the First Workshop in Intelligent Informatics and Smart Technology. Of the 66 high-quality papers accepted, this book presents twelve from the Symposium on Natural Language Processing track and ten from the Workshop in Intelligent Informatics and Smart Technology track (SSAI: Special Session on Artificial Intelligence).

Online Harassment is one of the most serious problems in social media. To address it requires understanding the forms harassment takes, how it impacts the targets, who harasses, and how technology that stands between users and social media can stop harassers and protect users. The field of Human-Computer Interaction provides a unique set of tools to address this challenge. This book brings together experts in theory, socio-technical systems, network analysis, text analysis, and machine learning to present a broad set of analyses and applications that improve our understanding of the harassment problem and how to address it. This book tackles the problem of harassment by addressing it in three major domains. First, chapters explore how harassment manifests, including extensive analysis of the Gamer Gate incident, stylistic features of different types of harassment, how gender differences affect misogynistic harassment. Then, we look at the results of harassment, including how it drives people offline and the impacts it has on targets. Finally, we address techniques for mitigating harassment, both through automated detection and filtering and interface options that users control. Together, many branches of HCI come together to provide a comprehensive look at the phenomenon of online harassment and to advance the field toward effective human-oriented solutions.

Describing the technologies to combine language resources flexibly as web services, this book provides valuable case studies for those who work in services computing, language resources, human-computer interaction (HCI), computer-supported cooperative work (CSCW), and service science. The authors have been operating the Language Grid, which wraps existing language resources as atomic language services and enables users to compose new services by combining them. From architecture level to service composition level, the book explains how to resolve infrastructural and operational difficulties in sharing and combining language resources, including interoperability of language service infrastructures, various types of language service policies, human services, and service failures.The research based on the authors' operating experiences of handling complicated issues such as intellectual property and interoperability of language resources contributes to exploitation of language resources as a service. On the other hand, both the analysis based on using services and the design of new services can bring significant results. A new style of multilingual communication supported by language services is worthy of analysis in HCI/CSCW, and the design process of language services is the focus of valuable case studies in service science. By using language resources in different ways based on the Language Grid, many activities are highly regarded by diverse communities. This book consists of four parts: (1) two types of language service platforms to interconnect language services across service grids, (2) various language service composition technologies that improve the reusability, efficiency, and accuracy of composite services, (3) research work and activities in creating language resources and services, and (4) various applications and tools for understanding and designing language services that well support intercultural collaboration.

This book presents the consolidated acoustic data for all phones in Standard Colloquial Bengali (SCB), commonly known as Bangla, a Bengali language used by 350 million people in India, Bangladesh, and the Bengali diaspora. The book analyzes the real speech of selected native speakers of the Bangla dialect to ensure that a proper acoustical database is available for the development of speech technologies. The acoustic data presented consists of averages and their normal spread, represented by the standard deviations of necessary acoustic parameters including e.g. formant information for multiple native speakers of both sexes. The study employs two important speech technologies:(1) text to speech synthesis (TTS) and (2) automatic speech recognition (ASR). The procedures, particularly those related to the use of technologies, are described in sufficient detail to enable researchers to use them to create technical acoustic databases for any other Indian dialect. The book offers a unique resource for scientists and industrial practitioners who are interested in the acoustic analysis and processing of Indian dialects to develop similar dialect databases of their own.

This open access book provides new methodological and theoretical insights into temporal reference and its linguistic expression, from a cross-linguistic experimental corpus pragmatics approach. Verbal tenses, in general, and more specifically the categories of tense, grammatical and lexical aspect are treated as cohesion ties contributing to the temporal coherence of a discourse, as well as to the cognitive temporal coherence of the mental representations built in the language comprehension process. As such, it investigates the phenomenon of temporal reference at the interface between corpus linguistics, theoretical linguistics and pragmatics, experimental pragmatics, psycholinguistics, natural language processing and machine translation.

This book is about machine translation (MT) and the classic problems associated with this language technology. It examines the causes of these problems and, for linguistic, rule-based systems, attributes the cause to language's ambiguity and complexity and their interplay in logic-driven processes. For non-linguistic, data-driven systems, the book attributes translation shortcomings to the very lack of linguistics. It then proposes a demonstrable way to relieve these drawbacks in the shape of a working translation model (Logos Model) that has taken its inspiration from key assumptions about psycholinguistic and neurolinguistic function. The book suggests that this brain-based mechanism is effective precisely because it bridges both linguistically driven and data-driven methodologies. It shows how simulation of this cerebral mechanism has freed this one MT model from the all-important, classic problem of complexity when coping with the ambiguities of language. Logos Model accomplishes this by a data-driven process that does not sacrifice linguistic knowledge, but that, like the brain, integrates linguistics within a data-driven process. As a consequence, the book suggests that the brain-like mechanism embedded in this model has the potential to contribute to further advances in machine translation in all its technological instantiations.

This book applies formal language and automata theory in the context of Tibetan computational linguistics; further, it constructs a Tibetan-spelling formal grammar system that generates a Tibetan-spelling formal language group, and an automata group that can recognize the language group. In addition, it investigates the application technologies of Tibetan-spelling formal language and automata. Given its creative and original approach, the book offers a valuable reference guide for researchers, teachers and graduate students in the field of computational linguistics.

This is the first volume that brings together research and practice from academic and industry settings and a combination of human and machine translation evaluation. Its comprehensive collection of papers by leading experts in human and machine translation quality and evaluation who situate current developments and chart future trends fills a clear gap in the literature. This is critical to the successful integration of translation technologies in the industry today, where the lines between human and machine are becoming increasingly blurred by technology: this affects the whole translation landscape, from students and trainers to project managers and professionals, including in-house and freelance translators, as well as, of course, translation scholars and researchers. The editors have broad experience in translation quality evaluation research, including investigations into professional practice with qualitative and quantitative studies, and the contributors are leading experts in their respective fields, providing a unique set of complementary perspectives on human and machine translation quality and evaluation, combining theoretical and applied approaches.

The two-volume set LNCS 10761 + 10762 constitutes revised selected papers from the CICLing 2017 conference which took place in Budapest, Hungary, in April 2017. The total of 90 papers presented in the two volumes was carefully reviewed and selected from numerous submissions. In addition, the proceedings contain 4 invited papers. The papers are organized in the following topical sections: Part I: general; morphology and text segmentation; syntax and parsing; word sense disambiguation; reference and coreference resolution; named entity recognition; semantics and text similarity; information extraction; speech recognition; applications to linguistics and the humanities. Part II: sentiment analysis; opinion mining; author profiling and authorship attribution; social network analysis; machine translation; text summarization; information retrieval and text classification; practical applications.

Many applications within natural language processing involve performing text-to-text transformations, i.e., given a text in natural language as input, systems are required to produce a version of this text (e.g., a translation), also in natural language, as output. Automatically evaluating the output of such systems is an important component in developing text-to-text applications. Two approaches have been proposed for this problem: (i) to compare the system outputs against one or more reference outputs using string matching-based evaluation metrics and (ii) to build models based on human feedback to predict the quality of system outputs without reference texts. Despite their popularity, reference-based evaluation metrics are faced with the challenge that multiple good (and bad) quality outputs can be produced by text-to-text approaches for the same input. This variation is very hard to capture, even with multiple reference texts. In addition, reference-based metrics cannot be used in production (e.g., online machine translation systems), when systems are expected to produce outputs for any unseen input. In this book, we focus on the second set of metrics, so-called Quality Estimation (QE) metrics, where the goal is to provide an estimate on how good or reliable the texts produced by an application are without access to gold-standard outputs. QE enables different types of evaluation that can target different types of users and applications. Machine learning techniques are used to build QE models with various types of quality labels and explicit features or learnt representations, which can then predict the quality of unseen system outputs. This book describes the topic of QE for text-to-text applications, covering quality labels, features, algorithms, evaluation, uses, and state-of-the-art approaches. It focuses on machine translation as application, since this represents most of the QE work done to date. It also briefly describes QE for several other applications, including text simplification, text summarization, grammatical error correction, and natural language generation.

This updated book expands upon prosody for recognition applications of speech processing. It includes importance of prosody for speech processing applications; builds on why prosody needs to be incorporated in speech processing applications; and presents methods for extraction and representation of prosody for applications such as speaker recognition, language recognition and speech recognition. The updated book also includes information on the significance of prosody for emotion recognition and various prosody-based approaches for automatic emotion recognition from speech.

Sentiment analysis and opinion mining is the field of study that analyzes people's opinions, sentiments, evaluations, attitudes, and emotions from written language. It is one of the most active research areas in natural language processing and is also widely studied in data mining, Web mining, and text mining. In fact, this research has spread outside of computer science to the management sciences and social sciences due to its importance to business and society as a whole. The growing importance of sentiment analysis coincides with the growth of social media such as reviews, forum discussions, blogs, micro-blogs, Twitter, and social networks. For the first time in human history, we now have a huge volume of opinionated data recorded in digital form for analysis. Sentiment analysis systems are being applied in almost every business and social domain because opinions are central to almost all human activities and are key influencers of our behaviors. Our beliefs and perceptions of reality, and the choices we make, are largely conditioned on how others see and evaluate the world. For this reason, when we need to make a decision we often seek out the opinions of others. This is true not only for individuals but also for organizations. This book is a comprehensive introductory and survey text. It covers all important topics and the latest developments in the field with over 400 references. It is suitable for students, researchers and practitioners who are interested in social media analysis in general and sentiment analysis in particular. Lecturers can readily use it in class for courses on natural language processing, social media analysis, text mining, and data mining. Lecture slides are also available online. Table of Contents: Preface / Sentiment Analysis: A Fascinating Problem / The Problem of Sentiment Analysis / Document Sentiment Classification / Sentence Subjectivity and Sentiment Classification / Aspect-Based Sentiment Analysis / Sentiment Lexicon Generation / Opinion Summarization / Analysis of Comparative Opinions / Opinion Search and Retrieval / Opinion Spam Detection / Quality of Reviews / Concluding Remarks / Bibliography / Author Biography