As online information grows dramatically, search engines such as Google are playing a more and more important role in our lives. Critical to all search engines is the problem of designing an effective retrieval model that can rank documents accurately for a given query. This has been a central research problem in information retrieval for several decades. In the past ten years, a new generation of retrieval models, often referred to as statistical language models, has been successfully applied to solve many different information retrieval problems. Compared with the traditional models such as the vector space model, these new models have a more sound statistical foundation and can leverage statistical estimation to optimize retrieval parameters. They can also be more easily adapted to model non-traditional and complex retrieval problems. Empirically, they tend to achieve comparable or better performance than a traditional model with less effort on parameter tuning. This book systematically reviews the large body of literature on applying statistical language models to information retrieval with an emphasis on the underlying principles, empirically effective language models, and language models developed for non-traditional retrieval tasks. All the relevant literature has been synthesized to make it easy for a reader to digest the research progress achieved so far and see the frontier of research in this area. The book also offers practitioners an informative introduction to a set of practically useful language models that can effectively solve a variety of retrieval problems. No prior knowledge about information retrieval is required, but some basic knowledge about probability and statistics would be useful for fully digesting all the details. Table of Contents: Introduction / Overview of Information Retrieval Models / Simple Query Likelihood Retrieval Model / Complex Query Likelihood Model / Probabilistic Distance Retrieval Model / Language Models for Special Retrieval Tasks / Language Models for Latent Topic Analysis / Conclusions

This book collects and introduces some of the best and most useful work in practical lexicography. It has been designed as a resource for students and scholars of lexicography and lexicology and to be an essential reference for professional lexicographers. It focusses on central issues in the field and covers topics hotly debated in lexicography circles. After a full contextual introduction Thierry Fontenelle divides the book into twelve parts - theoretical perspectives, corpus design, lexicographical evidence, word senses and polysemy, collocations and idioms, definitions, examples, grammar and usage, bilingual lexicography, tools and methods, semantic networks, and how dictionaries are used. The book is fully referenced and indexed.
The reader may be used independently for reference or as reading material for a course of study. It will also be an essential companion for The Oxford Guide to Practical Lexicography by Sue Atkins and Michael Rundell, to be published by OUP in 2008.

This book investigates the nature of generalization in language and examines how language is known by adults and acquired by children. It looks at how and why constructions are learned, the relation between their forms and functions, and how cross-linguistic and language-internal generalizations about them can be explained.
Constructions at Work is divided into three parts: in the first Professor Goldberg provides an overview of constructionist approaches, including the constructionist approach to argument structure, and argues for a usage-based model of grammar. In Part II she addresses issues concerning how generalizations are constrained and constructional generalizations are learned. In Part III the author shows that a combination of function and processing accounts for a wide range of language-internal and cross-linguistic generalizations. She then considers the degree to which the function of constructions explains their distribution and examines cross-linguistic tendencies in argument realization. She demonstrates that pragmatic and cognitive processes account for the data without appeal to stipulations that are language-specific.
This book is an important contribution to the study of how language operates in the mind and in the world and how these operations relate. It is of central interest for scholars and graduate-level students in all branches of theoretical linguistics and psycholinguistics. It will also appeal to cognitive scientists and philosophers concerned with language and its acquisition.

This groundbreaking book offers a new and compelling perspective on the structure of human language. The fundamental issue it addresses is the proper balance between syntax and semantics, between structure and derivation, and between rule systems and lexicon. It argues that the balance struck by mainstream generative grammar is wrong. It puts forward a new basis for syntactic theory, drawing on a wide range of frameworks, and charts new directions for research. In the past four decades, theories of syntactic structure have become more abstract, and syntactic derivations have become ever more complex. Peter Culicover and Ray Jackendoff trace this development through the history of contemporary syntactic theory, showing how much it has been driven by theory-internal rather than empirical considerations. They develop an alternative that is responsive to linguistic, cognitive, computational, and biological concerns. At the core of this alternative is the Simpler Syntax Hypothesis: the most explanatory syntactic theory is one that imputes the minimum structure necessary to mediate between phonology and meaning. A consequence of this hypothesis is a far richer mapping between syntax and semantics than is generally assumed. Through concrete analyses of numerous grammatical phenomena, some well studied and some new, the authors demonstrate the empirical and conceptual superiority of the Simpler Syntax approach. Simpler Syntax is addressed to linguists of all persuasions. It will also be of central interest to those concerned with language in psychology, human biology, evolution, computational science, and artificial intellige

This book provides a comprehensive introduction to Conversational AI. While the idea of interacting with a computer using voice or text goes back a long way, it is only in recent years that this idea has become a reality with the emergence of digital personal assistants, smart speakers, and chatbots. Advances in AI, particularly in deep learning, along with the availability of massive computing power and vast amounts of data, have led to a new generation of dialogue systems and conversational interfaces. Current research in Conversational AI focuses mainly on the application of machine learning and statistical data-driven approaches to the development of dialogue systems. However, it is important to be aware of previous achievements in dialogue technology and to consider to what extent they might be relevant to current research and development. Three main approaches to the development of dialogue systems are reviewed: rule-based systems that are handcrafted using best practice guidelines; statistical data-driven systems based on machine learning; and neural dialogue systems based on end-to-end learning. Evaluating the performance and usability of dialogue systems has become an important topic in its own right, and a variety of evaluation metrics and frameworks are described. Finally, a number of challenges for future research are considered, including: multimodality in dialogue systems, visual dialogue; data efficient dialogue model learning; using knowledge graphs; discourse and dialogue phenomena; hybrid approaches to dialogue systems development; dialogue with social robots and in the Internet of Things; and social and ethical issues.

Placing contemporary spoken English at the centre of phonological research, this book tackles the issue of language variation and change through a range of methodological and theoretical approaches. In doing so the book bridges traditionally separate fields such as experimental phonetics, theoretical phonology, language acquisition and sociolinguistics. Made up of 12 chapters, it explores a substantial range of linguistic phenomena. It covers auditory, acoustic and articulatory phonetics, second language pronunciation and perception, sociophonetics, cross-linguistic comparison of vowel reduction and methodological issues in the construction of phonological corpora. The book presents new data and analyses which demonstrate what phonologists, phoneticians and sociolinguists do with their corpora and show how various theoretical and experimental questions can be explored in light of authentic spoken data.

A landmark in linguistics and cognitive science. Ray Jackendoff proposes a new holistic theory of the relation between the sounds, structure, and meaning of language and their relation to mind and brain. Foundations of Language exhibits the most fundamental new thinking in linguistics since Noam Chomsky's Aspects of the Theory of Syntax in 1965 -- yet is readable, stylish, and accessible to a wide readership. Along the way it provides new insights on the evolution of language, thought, and communication.

This volume of newly commissioned essays examines current theoretical and computational work on polysemy, the term used in semantic analysis to describe words with more than one meaning. Such words present few difficulties in everyday language, but pose central problems for linguists and lexicographers, especially for those involved in lexical semantics and in computational modelling. The contributors to this book - leading researchers in theoretical and computational linguistics - consider the implications of these problems for linguistic theory and how they may be addressed by computational means. The theoretical essays in the book examine polysemy as an aspect of a broader theory of word meaning. Three theoretical approaches are presented: the Classical (or Aristotelian), the Prototypical, and the Relational. Their authors describe the nature of polysemy, the criteria for detecting it, and its manifestations across languages. They examine the issues arising from the regularity of polysemy and the theoretical principles proposed to account for the interaction of lexical meaning with the semantics and syntax of the context in which it occurs. Finally they consider the formal representations of meaning in the lexicon, and their implications for dictionary construction. The computational essays are concerned with the challenge of polysemy to automatic sense disambiguation - how the intended meaning for a word occurrence can be identified. The approaches presented include the exploitation of lexical information in machine-readable dictionaries, machine learning based on patterns of word co-occurrence, and hybrid approaches that combine the two. As a whole the volume shows how on the one hand theoretical work provides the motivation and may suggest the basis for computational algorithms, while on the other computational results may validate, or reveal problems in, the principles set forth by theories.

This book provides linguists with a clear, critical, and comprehensive overview of theoretical and experimental work on information structure. Leading researchers survey the main theories of information structure in syntax, phonology, and semantics as well as perspectives from psycholinguistics and other relevant fields. Following the editors' introduction the book is divided into four parts. The first, on theories of and theoretical perspectives on information structure, includes chapters on focus, topic, and givenness. Part 2 covers a range of current issues in the field, including quantification, dislocation, and intonation, while Part 3 is concerned with experimental approaches to information structure, including language processing and acquisition. The final part contains a series of linguistic case studies drawn from a wide variety of the world's language families. This volume will be the standard guide to current work in information structure and a major point of departure for future research.

Argumentation mining is an application of natural language processing (NLP) that emerged a few years ago and has recently enjoyed considerable popularity, as demonstrated by a series of international workshops and by a rising number of publications at the major conferences and journals of the field. Its goals are to identify argumentation in text or dialogue; to construct representations of the constellation of claims, supporting and attacking moves (in different levels of detail); and to characterize the patterns of reasoning that appear to license the argumentation. Furthermore, recent work also addresses the difficult tasks of evaluating the persuasiveness and quality of arguments. Some of the linguistic genres that are being studied include legal text, student essays, political discourse and debate, newspaper editorials, scientific writing, and others. The book starts with a discussion of the linguistic perspective, characteristics of argumentative language, and their relationship to certain other notions such as subjectivity. Besides the connection to linguistics, argumentation has for a long time been a topic in Artificial Intelligence, where the focus is on devising adequate representations and reasoning formalisms that capture the properties of argumentative exchange. It is generally very difficult to connect the two realms of reasoning and text analysis, but we are convinced that it should be attempted in the long term, and therefore we also touch upon some fundamentals of reasoning approaches. Then the book turns to its focus, the computational side of mining argumentation in text. We first introduce a number of annotated corpora that have been used in the research. From the NLP perspective, argumentation mining shares subtasks with research fields such as subjectivity and sentiment analysis, semantic relation extraction, and discourse parsing. Therefore, many technical approaches are being borrowed from those (and other) fields. We break argumentation mining into a series of subtasks, starting with the preparatory steps of classifying text as argumentative (or not) and segmenting it into elementary units. Then, central steps are the automatic identification of claims, and finding statements that support or oppose the claim. For certain applications, it is also of interest to compute a full structure of an argumentative constellation of statements. Next, we discuss a few steps that try to 'dig deeper': to infer the underlying reasoning pattern for a textual argument, to reconstruct unstated premises (so-called 'enthymemes'), and to evaluate the quality of the argumentation. We also take a brief look at 'the other side' of mining, i.e., the generation or synthesis of argumentative text. The book finishes with a summary of the argumentation mining tasks, a sketch of potential applications, and a--necessarily subjective--outlook for the field.

Recent developments in artificial intelligence, especially neural network and deep learning technology, have led to rapidly improving performance in voice assistants such as Siri and Alexa. Over the next few years, capability will continue to improve and become increasingly personalised. Today's voice assistants will evolve into virtual personal assistants firmly embedded within our everyday lives. Told through the view of a fictitious personal assistant called Cyba, this book provides an accessible but detailed overview of how a conversational voice assistant works, especially how it understands spoken language, manages conversations, answers questions and generates responses. Cyba explains through examples and diagrams the neural network technology underlying speech recognition and synthesis, natural language understanding, knowledge representation, conversation management, language translation and chatbot technology. Cyba also explores the implications of this rapidly evolving technology for security, privacy and bias, and gives a glimpse of future developments. Cyba's website can be found at HeyCyba.com.

The topic of this book is the theoretical foundations of a theory LSLT -- Lexical Semantic Language Theory - and its implementation in a the system for text analysis and understanding called GETARUN, developed at the University of Venice, Laboratory of Computational Linguistics, Department of Language Sciences. LSLT encompasses a psycholinguistic theory of the way the language faculty works, a grammatical theory of the way in which sentences are analysed and generated -- for this we will be using Lexical-Functional Grammar -- a semantic theory of the way in which meaning is encoded and expressed in utterances -- for this we will be using Situation Semantics -, and a parsing theory of the way in which components of the theory interact in a common architecture to produce the needed language representation to be eventually spoken aloud or interpreted by the phonetic/acoustic language interface. LSLT will then be put to use to show how discourse relations are mapped automatically from text using the tools available in the 4 sub-theories, and in particular we will focus on Causal Relations showing how the various sub-theories contribute to address different types of causality.

This handbook explores multiple facets of the study of word classes, also known as parts of speech or lexical categories. These categories are of fundamental importance to linguistic theory and description, both formal and functional, and for both language-internal analyses and cross-linguistic comparison. The volume consists of five parts that investigate word classes from different angles. Chapters in the first part address a range of fundamental issues including diversity and unity in word classes around the world, categorization at different levels of structure, the distinction between lexical and functional words, and hybrid categories. Part II examines the treatment of word classes across a wide range of contemporary linguistic theories, such as Cognitive Grammar, Minimalist Syntax, and Lexical Functional Grammar, while the focus of Part III is on individual word classes, from major categories such as verb and noun to minor ones such as adpositions and ideophones. Part IV provides a number of cross-linguistic case studies, exploring word classes in families including Afroasiatic, Sinitic, Mayan, Austronesian, and in sign languages. Chapters in the final part of the book discuss word classes from the perspective of various sub-disciplines of linguistics, ranging from first and second language acquisition to computational and corpus linguistics. Together, the contributions showcase the importance of word classes for the whole discipline of linguistics, while also highlighting the many ongoing debates in the areas and outlining fruitful avenues for future research.

This book provides a computational re-evaluation of the genealogical relations between the early Germanic families and of their diversification from their most recent common ancestor, Proto-Germanic. It also proposes a novel computational approach to the problem of linguistic diversification more broadly, using agent-based simulation of speech communities over time. This new method is presented alongside more traditional phylogenetic inference, and the respective results are compared and evaluated. Frederik Hartmann demonstrates that the traditional and novel methods each capture different aspects of this highly complex real-world process; crucially, the new computational approach proposed here offers a new way of investigating the wave-like properties of language relatedness that were previously less accessible. As well as validating the findings of earlier research, the results of this study also generate new insights and shed light on much-debated issues in the field. The conclusion is that the break-up of Germanic should be understood as a gradual disintegration process in which tree-like branching effects are rare.

In this brief, the authors discuss recently explored spectral (sub-segmental and pitch synchronous) and prosodic (global and local features at word and syllable levels in different parts of the utterance) features for discerning emotions in a robust manner. The authors also delve into the complementary evidences obtained from excitation source, vocal tract system and prosodic features for the purpose of enhancing emotion recognition performance. Features based on speaking rate characteristics are explored with the help of multi-stage and hybrid models for further improving emotion recognition performance. Proposed spectral and prosodic features are evaluated on real life emotional speech corpus.

In everyday communication, Europe's citizens, business partners and politicians are inevitably confronted with language barriers. Language technology has the potential to overcome these barriers and to provide innovative interfaces to technologies and knowledge. This document presents a Strategic Research Agenda for Multilingual Europe 2020. The agenda was prepared by META-NET, a European Network of Excellence. META-NET consists of 60 research centres in 34 countries, who cooperate with stakeholders from economy, government agencies, research organisations, non-governmental organisations, language communities and European universities. META-NET's vision is high-quality language technology for all European languages. "The research carried out in the area of language technology is of utmost importance for the consolidation of Portuguese as a language of global communication in the information society." - Dr. Pedro Passos Coelho (Prime-Minister of Portugal) "It is imperative that language technologies for Slovene are developed systematically if we want Slovene to flourish also in the future digital world." - Dr. Danilo Turk (President of the Republic of Slovenia) "For such small languages like Latvian keeping up with the ever increasing pace of time and technological development is crucial. The only way to ensure future existence of our language is to provide its users with equal opportunities as the users of larger languages enjoy. Therefore being on the forefront of modern technologies is our opportunity." - Valdis Dombrovskis (Prime Minister of Latvia) "Europe's inherent multilingualism and our scientific expertise are the perfect prerequisites for significantly advancing the challenge that language technology poses. META-NET opens up new opportunities for the development of ubiquitous multilingual technologies." - Prof. Dr. Annette Schavan (German Minister of Education and Research)

Metadata such as the hashtag is an important dimension of social media communication. Despite its important role in practices such as curating, tagging, and searching content, there has been little research into how meanings are made with social metadata. This book considers how hashtags have expanded their reach from an information-locating resource to an interpersonal resource for coordinating social relationships and expressing solidarity, affinity, and affiliation. It adopts a social semiotic perspective to investigate the communicative functions of hashtags in relation to both language and images. This book is a follow up to Zappavigna's 2012 model of ambient affiliation, providing an extended analytical framework for exploring how affiliation occurs, bond by bond, in online discourse. It focuses in particular on the communing function of hashtags in metacommentary and ridicule, using recent Twitter discourse about US President Donald Trump as a case study. It is essential reading for researchers as well as undergraduates studying social media on any academic course.

This handbook offers a comprehensive overview of the field of Persian linguistics, discusses its development, and captures critical accounts of cutting edge research within its major subfields, as well as outlining current debates and suggesting productive lines of future research. Leading scholars in the major subfields of Persian linguistics examine a range of topics split into six thematic parts. Following a detailed introduction from the editors, the volume begins by placing Persian in its historical and typological context in Part I. Chapters in Part II examine topics relating to phonetics and phonology, while Part III looks at approaches to and features of Persian syntax. The fourth part of the volume explores morphology and lexicography, as well as the work of the Academy of Persian Language and Literature. Part V, language and people, covers topics such as language contact and teaching Persian as a foreign language, while the final part examines psycho- neuro-, and computational linguistics. The volume will be an essential resource for all scholars with an interest in Persian language and linguistics.

This handbook compares the main analytic frameworks and methods of contemporary linguistics. It offers a unique overview of linguistic theory, revealing the common concerns of competing approaches. By showing their current and potential applications it provides the means by which linguists and others can judge what are the most useful models for the task in hand. Distinguished scholars from all over the world explain the rationale and aims of over thirty explanatory approaches to the description, analysis, and understanding of language. Each chapter considers the main goals of the model; the relation it proposes from between lexicon, syntax, semantics, pragmatics, and phonology; the way it defines the interactions between cognition and grammar; what it counts as evidence; and how it explains linguistic change and structure. The Oxford Handbook of Linguistic Analysis offers an indispensable guide for everyone researching any aspect of language including those in linguistics, comparative philology, cognitive science, developmental philology, cognitive science, developmental psychology, computational science, and artificial intelligence. This second edition has been updated to include seven new chapters looking at linguistic units in language acquisition, conversation analysis, neurolinguistics, experimental phonetics, phonological analysis, experimental semantics, and distributional typology.

This book is about a new approach in the field of computational linguistics related to the idea of constructing n-grams in non-linear manner, while the traditional approach consists in using the data from the surface structure of texts, i.e., the linear structure.In this book, we propose and systematize the concept of syntactic n-grams, which allows using syntactic information within the automatic text processing methods related to classification or clustering. It is a very interesting example of application of linguistic information in the automatic (computational) methods. Roughly speaking, the suggestion is to follow syntactic trees and construct n-grams based on paths in these trees. There are several types of non-linear n-grams; future work should determine, which types of n-grams are more useful in which natural language processing (NLP) tasks. This book is intended for specialists in the field of computational linguistics. However, we made an effort to explain in a clear manner how to use n-grams; we provide a large number of examples, and therefore we believe that the book is also useful for graduate students who already have some previous background in the field.

With a machine learning approach and less focus on linguistic details, this gentle introduction to natural language processing develops fundamental mathematical and deep learning models for NLP under a unified framework. NLP problems are systematically organised by their machine learning nature, including classification, sequence labelling, and sequence-to-sequence problems. Topics covered include statistical machine learning and deep learning models, text classification and structured prediction models, generative and discriminative models, supervised and unsupervised learning with latent variables, neural networks, and transition-based methods. Rich connections are drawn between concepts throughout the book, equipping students with the tools needed to establish a deep understanding of NLP solutions, adapt existing models, and confidently develop innovative models of their own. Featuring a host of examples, intuition, and end of chapter exercises, plus sample code available as an online resource, this textbook is an invaluable tool for the upper undergraduate and graduate student.

This book is an advanced introduction to semantics that presents this crucial component of human language through the lens of the 'Meaning-Text' theory - an approach that treats linguistic knowledge as a huge inventory of correspondences between thought and speech. Formally, semantics is viewed as an organized set of rules that connect a representation of meaning (Semantic Representation) to a representation of the sentence (Deep-Syntactic Representation). The approach is particularly interesting for computer assisted language learning, natural language processing and computational lexicography, as our linguistic rules easily lend themselves to formalization and computer applications. The model combines abstract theoretical constructions with numerous linguistic descriptions, as well as multiple practice exercises that provide a solid hands-on approach to learning how to describe natural language semantics.

This white paper is part of a series that promotes knowledge about language technology and its potential. It addresses educators, journalists, politicians, language communities and others. The availability and use of language technology in Europe varies between languages. Consequently, the actions that are required to further support research and development of language technologies also differ for each language. The required actions depend on many factors, such as the complexity of a given language and the size of its community. META-NET, a Network of Excellence funded by the European Commission, has conducted an analysis of current language resources and technologies. This analysis focused on the 23 official European languages as well as other important national and regional languages in Europe. The results of this analysis suggest that there are many significant research gaps for each language. A more detailed expert analysis and assessment of the current situation will help maximise the impact of additional research and minimize any risks. META-NET consists of 54 research centres from 33 countries that are working with stakeholders from commercial businesses, government agencies, industry, research organisations, software companies, technology providers and European universities. Together, they are creating a common technology vision while developing a strategic research agenda that shows how language technology applications can address any research gaps by 2020.