Naturligt sprog og maskinoversættelse

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.

This book covers the topic of temporal tagging, the detection of temporal expressions and the normalization of their semantics to some standard format. It places a special focus on the challenges and opportunities of domain-sensitive temporal tagging. After providing background knowledge on the concept of time, the book continues with a comprehensive survey of current research on temporal tagging. The authors provide an overview of existing techniques and tools, and highlight key issues that need to be addressed. This book is a valuable resource for researchers and application developers who need to become familiar with the topic and want to know the recent trends, current tools and techniques, as well as different application domains in which temporal information is of utmost importance. Due to the prevalence of temporal expressions in diverse types of documents and the importance of temporal information in any information space, temporal tagging is an important task in natural language processing (NLP), and applications of several domains can benefit from the output of temporal taggers to provide more meaningful and useful results. In recent years, temporal tagging has been an active field in NLP and computational linguistics. Several approaches to temporal tagging have been proposed, annotation standards have been developed, gold standard data sets have been created, and research competitions have been organized. Furthermore, some temporal taggers have also been made publicly available so that temporal tagging output is not just exploited in research, but is finding its way into real world applications. In addition, this book particularly focuses on domain-specific temporal tagging of documents. This is a crucial aspect as different types of documents (e.g., news articles, narratives, and colloquial texts) result in diverse challenges for temporal taggers and should be processed in a domain-sensitive manner.

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.

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.

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.

This book discusses the state of the art of automated essay scoring, its challenges and its potential. One of the earliest applications of artificial intelligence to language data (along with machine translation and speech recognition), automated essay scoring has evolved to become both a revenue-generating industry and a vast field of research, with many subfields and connections to other NLP tasks. In this book, we review the developments in this field against the backdrop of Elias Page's seminal 1966 paper titled "e;The Imminence of Grading Essays by Computer."e; Part 1 establishes what automated essay scoring is about, why it exists, where the technology stands, and what are some of the main issues. In Part 2, the book presents guided exercises to illustrate how one would go about building and evaluating a simple automated scoring system, while Part 3 offers readers a survey of the literature on different types of scoring models, the aspects of essay quality studied in prior research, and the implementation and evaluation of a scoring engine. Part 4 offers a broader view of the field inclusive of some neighboring areas, and Part \ref{part5} closes with summary and discussion. This book grew out of a week-long course on automated evaluation of language production at the North American Summer School for Logic, Language, and Information (NASSLLI), attended by advanced undergraduates and early-stage graduate students from a variety of disciplines. Teachers of natural language processing, in particular, will find that the book offers a useful foundation for a supplemental module on automated scoring. Professionals and students in linguistics, applied linguistics, educational technology, and other related disciplines will also find the material here useful.

This book provides a thorough introduction to the subfield of theoretical computer science known as grammatical inference from a computational linguistic perspective. Grammatical inference provides principled methods for developing computationally sound algorithms that learn structure from strings of symbols. The relationship to computational linguistics is natural because many research problems in computational linguistics are learning problems on words, phrases, and sentences: What algorithm can take as input some finite amount of data (for instance a corpus, annotated or otherwise) and output a system that behaves "e;correctly"e; on specific tasks? Throughout the text, the key concepts of grammatical inference are interleaved with illustrative examples drawn from problems in computational linguistics. Special attention is paid to the notion of "e;learning bias."e; In the context of computational linguistics, such bias can be thought to reflect common (ideally universal) properties of natural languages. This bias can be incorporated either by identifying a learnable class of languages which contains the language to be learned or by using particular strategies for optimizing parameter values. Examples are drawn largely from two linguistic domains (phonology and syntax) which span major regions of the Chomsky Hierarchy (from regular to context-sensitive classes). The conclusion summarizes the major lessons and open questions that grammatical inference brings to computational linguistics. Table of Contents: List of Figures / List of Tables / Preface / Studying Learning / Formal Learning / Learning Regular Languages / Learning Non-Regular Languages / Lessons Learned and Open Problems / Bibliography / Author Biographies

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.

The literary imagination may take flight on the wings of metaphor, but hard-headed scientists are just as likely as doe-eyed poets to reach for a metaphor when the descriptive need arises. Metaphor is a pervasive aspect of every genre of text and every register of speech, and is as useful for describing the inner workings of a "e;black hole"e; (itself a metaphor) as it is the affairs of the human heart. The ubiquity of metaphor in natural language thus poses a significant challenge for Natural Language Processing (NLP) systems and their builders, who cannot afford to wait until the problems of literal language have been solved before turning their attention to figurative phenomena. This book offers a comprehensive approach to the computational treatment of metaphor and its figurative brethren-including simile, analogy, and conceptual blending-that does not shy away from their important cognitive and philosophical dimensions. Veale, Shutova, and Beigman Klebanov approach metaphor from multiple computational perspectives, providing coverage of both symbolic and statistical approaches to interpretation and paraphrase generation, while also considering key contributions from philosophy on what constitutes the "e;meaning"e; of a metaphor. This book also surveys available metaphor corpora and discusses protocols for metaphor annotation. Any reader with an interest in metaphor, from beginning researchers to seasoned scholars, will find this book to be an invaluable guide to what is a fascinating linguistic phenomenon.

Artificial Intelligence federates numerous scientific fields in the aim of developing machines able to assist human operators performing complex treatments---most of which demand high cognitive skills (e.g. learning or decision processes). Central to this quest is to give machines the ability to estimate the likeness or similarity between things in the way human beings estimate the similarity between stimuli. In this context, this book focuses on semantic measures: approaches designed for comparing semantic entities such as units of language, e.g. words, sentences, or concepts and instances defined into knowledge bases. The aim of these measures is to assess the similarity or relatedness of such semantic entities by taking into account their semantics, i.e. their meaning---intuitively, the words tea and coffee, which both refer to stimulating beverage, will be estimated to be more semantically similar than the words toffee (confection) and coffee, despite that the last pair has a higher syntactic similarity. The two state-of-the-art approaches for estimating and quantifying semantic similarities/relatedness of semantic entities are presented in detail: the first one relies on corpora analysis and is based on Natural Language Processing techniques and semantic models while the second is based on more or less formal, computer-readable and workable forms of knowledge such as semantic networks, thesauri or ontologies. Semantic measures are widely used today to compare units of language, concepts, instances or even resources indexed by them (e.g., documents, genes). They are central elements of a large variety of Natural Language Processing applications and knowledge-based treatments, and have therefore naturally been subject to intensive and interdisciplinary research efforts during last decades. Beyond a simple inventory and categorization of existing measures, the aim of this monograph is to convey novices as well as researchers of these domains toward a better understanding of semantic similarity estimation and more generally semantic measures. To this end, we propose an in-depth characterization of existing proposals by discussing their features, the assumptions on which they are based and empirical results regarding their performance in particular applications. By answering these questions and by providing a detailed discussion on the foundations of semantic measures, our aim is to give the reader key knowledge required to: (i) select the more relevant methods according to a particular usage context, (ii) understand the challenges offered to this field of study, (iii) distinguish room of improvements for state-of-the-art approaches and (iv) stimulate creativity toward the development of new approaches. In this aim, several definitions, theoretical and practical details, as well as concrete applications are presented.

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.

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 "e;in-house"e; 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.

Learning to rank refers to machine learning techniques for training a model in a ranking task. Learning to rank is useful for many applications in information retrieval, natural language processing, and data mining. Intensive studies have been conducted on its problems recently, and significant progress has been made. This lecture gives an introduction to the area including the fundamental problems, major approaches, theories, applications, and future work. The author begins by showing that various ranking problems in information retrieval and natural language processing can be formalized as two basic ranking tasks, namely ranking creation (or simply ranking) and ranking aggregation. In ranking creation, given a request, one wants to generate a ranking list of offerings based on the features derived from the request and the offerings. In ranking aggregation, given a request, as well as a number of ranking lists of offerings, one wants to generate a new ranking list of the offerings. Ranking creation (or ranking) is the major problem in learning to rank. It is usually formalized as a supervised learning task. The author gives detailed explanations on learning for ranking creation and ranking aggregation, including training and testing, evaluation, feature creation, and major approaches. Many methods have been proposed for ranking creation. The methods can be categorized as the pointwise, pairwise, and listwise approaches according to the loss functions they employ. They can also be categorized according to the techniques they employ, such as the SVM based, Boosting based, and Neural Network based approaches. The author also introduces some popular learning to rank methods in details. These include: PRank, OC SVM, McRank, Ranking SVM, IR SVM, GBRank, RankNet, ListNet & ListMLE, AdaRank, SVM MAP, SoftRank, LambdaRank, LambdaMART, Borda Count, Markov Chain, and CRanking. The author explains several example applications of learning to rank including web search, collaborative filtering, definition search, keyphrase extraction, query dependent summarization, and re-ranking in machine translation. A formulation of learning for ranking creation is given in the statistical learning framework. Ongoing and future research directions for learning to rank are also discussed. Table of Contents: Learning to Rank / Learning for Ranking Creation / Learning for Ranking Aggregation / Methods of Learning to Rank / Applications of Learning to Rank / Theory of Learning to Rank / Ongoing and Future Work

This book conveys the fundamentals of Linked Lexical Knowledge Bases (LLKB) and sheds light on their different aspects from various perspectives, focusing on their construction and use in natural language processing (NLP). It characterizes a wide range of both expert-based and collaboratively constructed lexical knowledge bases. Only basic familiarity with NLP is required and this book has been written for both students and researchers in NLP and related fields who are interested in knowledge-based approaches to language analysis and their applications. Lexical Knowledge Bases (LKBs) are indispensable in many areas of natural language processing, as they encode human knowledge of language in machine readable form, and as such, they are required as a reference when machines attempt to interpret natural language in accordance with human perception. In recent years, numerous research efforts have led to the insight that to make the best use of available knowledge, the orchestrated exploitation of different LKBs is necessary. This allows us to not only extend the range of covered words and senses, but also gives us the opportunity to obtain a richer knowledge representation when a particular meaning of a word is covered in more than one resource. Examples where such an orchestrated usage of LKBs proved beneficial include word sense disambiguation, semantic role labeling, semantic parsing, and text classification. This book presents different kinds of automatic, manual, and collaborative linkings between LKBs. A special chapter is devoted to the linking algorithms employing text-based, graph-based, and joint modeling methods. Following this, it presents a set of higher-level NLP tasks and algorithms, effectively utilizing the knowledge in LLKBs. Among them, you will find advanced methods, e.g., distant supervision, or continuous vector space models of knowledge bases (KB), that have become widely used at the time of this book's writing. Finally, multilingual applications of LLKB's, such as cross-lingual semantic relatedness and computer-aided translation are discussed, as well as tools and interfaces for exploring LLKBs, followed by conclusions and future research directions.

Neural networks are a family of powerful machine learning models. This book focuses on the application of neural network models to natural language data. The first half of the book (Parts I and II) covers the basics of supervised machine learning and feed-forward neural networks, the basics of working with machine learning over language data, and the use of vector-based rather than symbolic representations for words. It also covers the computation-graph abstraction, which allows to easily define and train arbitrary neural networks, and is the basis behind the design of contemporary neural network software libraries.The second part of the book (Parts III and IV) introduces more specialized neural network architectures, including 1D convolutional neural networks, recurrent neural networks, conditioned-generation models, and attention-based models. These architectures and techniques are the driving force behind state-of-the-art algorithms for machine translation, syntactic parsing, and many other applications. Finally, we also discuss tree-shaped networks, structured prediction, and the prospects of multi-task learning.

For humans, understanding a natural language sentence or discourse is so effortless that we hardly ever think about it. For machines, however, the task of interpreting natural language, especially grasping meaning beyond the literal content, has proven extremely difficult and requires a large amount of background knowledge. This book focuses on the interpretation of natural language with respect to specific domain knowledge captured in ontologies. The main contribution is an approach that puts ontologies at the center of the interpretation process. This means that ontologies not only provide a formalization of domain knowledge necessary for interpretation but also support and guide the construction of meaning representations. We start with an introduction to ontologies and demonstrate how linguistic information can be attached to them by means of the ontology lexicon model lemon. These lexica then serve as basis for the automatic generation of grammars, which we use to compositionally construct meaning representations that conform with the vocabulary of an underlying ontology. As a result, the level of representational granularity is not driven by language but by the semantic distinctions made in the underlying ontology and thus by distinctions that are relevant in the context of a particular domain. We highlight some of the challenges involved in the construction of ontology-based meaning representations, and show how ontologies can be exploited for ambiguity resolution and the interpretation of temporal expressions. Finally, we present a question answering system that combines all tools and techniques introduced throughout the book in a real-world application, and sketch how the presented approach can scale to larger, multi-domain scenarios in the context of the Semantic Web. Table of Contents: List of Figures / Preface / Acknowledgments / Introduction / Ontologies / Linguistic Formalisms / Ontology Lexica / Grammar Generation / Putting Everything Together / Ontological Reasoning for Ambiguity Resolution / Temporal Interpretation / Ontology-Based Interpretation for Question Answering / Conclusion / Bibliography / Authors' Biographies

This unique book provides a comprehensive introduction to the most popular syntax-based statistical machine translation models, filling a gap in the current literature for researchers and developers in human language technologies. While phrase-based models have previously dominated the field, syntax-based approaches have proved a popular alternative, as they elegantly solve many of the shortcomings of phrase-based models. The heart of this book is a detailed introduction to decoding for syntax-based models. The book begins with an overview of synchronous-context free grammar (SCFG) and synchronous tree-substitution grammar (STSG) along with their associated statistical models. It also describes how three popular instantiations (Hiero, SAMT, and GHKM) are learned from parallel corpora. It introduces and details hypergraphs and associated general algorithms, as well as algorithms for decoding with both tree and string input. Special attention is given to efficiency, including search approximations such as beam search and cube pruning, data structures, and parsing algorithms. The book consistently highlights the strengths (and limitations) of syntax-based approaches, including their ability to generalize phrase-based translation units, their modeling of specific linguistic phenomena, and their function of structuring the search space.

Weighted finite-state transducers (WFSTs) are commonly used by engineers and computational linguists for processing and generating speech and text. This book first provides a detailed introduction to this formalism. It then introduces Pynini, a Python library for compiling finite-state grammars and for combining, optimizing, applying, and searching finite-state transducers. This book illustrates this library's conventions and use with a series of case studies. These include the compilation and application of context-dependent rewrite rules, the construction of morphological analyzers and generators, and text generation and processing applications.

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.

Thanks to the availability of texts on the Web in recent years, increased knowledge and information have been made available to broader audiences. However, the way in which a text is written-its vocabulary, its syntax-can be difficult to read and understand for many people, especially those with poor literacy, cognitive or linguistic impairment, or those with limited knowledge of the language of the text. Texts containing uncommon words or long and complicated sentences can be difficult to read and understand by people as well as difficult to analyze by machines. Automatic text simplification is the process of transforming a text into another text which, ideally conveying the same message, will be easier to read and understand by a broader audience. The process usually involves the replacement of difficult or unknown phrases with simpler equivalents and the transformation of long and syntactically complex sentences into shorter and less complex ones. Automatic text simplification, a research topic which started 20 years ago, now has taken on a central role in natural language processing research not only because of the interesting challenges it posesses but also because of its social implications. This book presents past and current research in text simplification, exploring key issues including automatic readability assessment, lexical simplification, and syntactic simplification. It also provides a detailed account of machine learning techniques currently used in simplification, describes full systems designed for specific languages and target audiences, and offers available resources for research and development together with text simplification evaluation techniques.

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.

In the last few years, a number of NLP researchers have developed and participated in the task of Recognizing Textual Entailment (RTE). This task encapsulates Natural Language Understanding capabilities within a very simple interface: recognizing when the meaning of a text snippet is contained in the meaning of a second piece of text. This simple abstraction of an exceedingly complex problem has broad appeal partly because it can be conceived also as a component in other NLP applications, from Machine Translation to Semantic Search to Information Extraction. It also avoids commitment to any specific meaning representation and reasoning framework, broadening its appeal within the research community. This level of abstraction also facilitates evaluation, a crucial component of any technological advancement program. This book explains the RTE task formulation adopted by the NLP research community, and gives a clear overview of research in this area. It draws out commonalities in this research, detailing the intuitions behind dominant approaches and their theoretical underpinnings. This book has been written with a wide audience in mind, but is intended to inform all readers about the state of the art in this fascinating field, to give a clear understanding of the principles underlying RTE research to date, and to highlight the short- and long-term research goals that will advance this technology.

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.

The field of narrative (or story) understanding and generation is one of the oldest in natural language processing (NLP) and artificial intelligence (AI), which is hardly surprising, since storytelling is such a fundamental and familiar intellectual and social activity. In recent years, the demands of interactive entertainment and interest in the creation of engaging narratives with life-like characters have provided a fresh impetus to this field. This book provides an overview of the principal problems, approaches, and challenges faced today in modeling the narrative structure of stories. The book introduces classical narratological concepts from literary theory and their mapping to computational approaches. It demonstrates how research in AI and NLP has modeled character goals, causality, and time using formalisms from planning, case-based reasoning, and temporal reasoning, and discusses fundamental limitations in such approaches. It proposes new representations for embedded narratives and fictional entities, for assessing the pace of a narrative, and offers an empirical theory of audience response. These notions are incorporated into an annotation scheme called NarrativeML. The book identifies key issues that need to be addressed, including annotation methods for long literary narratives, the representation of modality and habituality, and characterizing the goals of narrators. It also suggests a future characterized by advanced text mining of narrative structure from large-scale corpora and the development of a variety of useful authoring aids. This is the first book to provide a systematic foundation that integrates together narratology, AI, and computational linguistics. It can serve as a narratology primer for computer scientists and an elucidation of computational narratology for literary theorists. It is written in a highly accessible manner and is intended for use by a broad scientific audience that includes linguists (computational and formal semanticists), AI researchers, cognitive scientists, computer scientists, game developers, and narrative theorists. Table of Contents: List of Figures / List of Tables / Narratological Background / Characters as Intentional Agents / Time / Plot / Summary and Future Directions

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

The World Wide Web constitutes the largest existing source of texts written in a great variety of languages. A feasible and sound way of exploiting this data for linguistic research is to compile a static corpus for a given language. There are several adavantages of this approach: (i) Working with such corpora obviates the problems encountered when using Internet search engines in quantitative linguistic research (such as non-transparent ranking algorithms). (ii) Creating a corpus from web data is virtually free. (iii) The size of corpora compiled from the WWW may exceed by several orders of magnitudes the size of language resources offered elsewhere. (iv) The data is locally available to the user, and it can be linguistically post-processed and queried with the tools preferred by her/him. This book addresses the main practical tasks in the creation of web corpora up to giga-token size. Among these tasks are the sampling process (i.e., web crawling) and the usual cleanups including boilerplate removal and removal of duplicated content. Linguistic processing and problems with linguistic processing coming from the different kinds of noise in web corpora are also covered. Finally, the authors show how web corpora can be evaluated and compared to other corpora (such as traditionally compiled corpora). For additional material please visit the companion website: sites.morganclaypool.com/wccTable of Contents: Preface / Acknowledgments / Web Corpora / Data Collection / Post-Processing / Linguistic Processing / Corpus Evaluation and Comparison / Bibliography / Authors' Biographies

Discourse Processing here is framed as marking up a text with structural descriptions on several levels, which can serve to support many language-processing or text-mining tasks. We first explore some ways of assigning structure on the document level: the logical document structure as determined by the layout of the text, its genre-specific content structure, and its breakdown into topical segments. Then the focus moves to phenomena of local coherence. We introduce the problem of coreference and look at methods for building chains of coreferring entities in the text. Next, the notion of coherence relation is introduced as the second important factor of local coherence. We study the role of connectives and other means of signaling such relations in text, and then return to the level of larger textual units, where tree or graph structures can be ascribed by recursively assigning coherence relations. Taken together, these descriptions can inform text summarization, information extraction, discourse-aware sentiment analysis, question answering, and the like. Table of Contents: Introduction / Large Discourse Units and Topics / Coreference Resolution / Small Discourse Units and Coherence Relations / Summary: Text Structure on Multiple Interacting Levels

This book introduces basic supervised learning algorithms applicable to natural language processing (NLP) and shows how the performance of these algorithms can often be improved by exploiting the marginal distribution of large amounts of unlabeled data. One reason for that is data sparsity, i.e., the limited amounts of data we have available in NLP. However, in most real-world NLP applications our labeled data is also heavily biased. This book introduces extensions of supervised learning algorithms to cope with data sparsity and different kinds of sampling bias. This book is intended to be both readable by first-year students and interesting to the expert audience. My intention was to introduce what is necessary to appreciate the major challenges we face in contemporary NLP related to data sparsity and sampling bias, without wasting too much time on details about supervised learning algorithms or particular NLP applications. I use text classification, part-of-speech tagging, and dependency parsing as running examples, and limit myself to a small set of cardinal learning algorithms. I have worried less about theoretical guarantees ("this algorithm never does too badly") than about useful rules of thumb ("in this case this algorithm may perform really well"). In NLP, data is so noisy, biased, and non-stationary that few theoretical guarantees can be established and we are typically left with our gut feelings and a catalogue of crazy ideas. I hope this book will provide its readers with both. Throughout the book we include snippets of Python code and empirical evaluations, when relevant.

It has been estimated that over a billion people are using or learning English as a second or foreign language, and the numbers are growing not only for English but for other languages as well. These language learners provide a burgeoning market for tools that help identify and correct learners' writing errors. Unfortunately, the errors targeted by typical commercial proofreading tools do not include those aspects of a second language that are hardest to learn. This volume describes the types of constructions English language learners find most difficult: constructions containing prepositions, articles, and collocations. It provides an overview of the automated approaches that have been developed to identify and correct these and other classes of learner errors in a number of languages. Error annotation and system evaluation are particularly important topics in grammatical error detection because there are no commonly accepted standards. Chapters in the book describe the options available to researchers, recommend best practices for reporting results, and present annotation and evaluation schemes. The final chapters explore recent innovative work that opens new directions for research. It is the authors' hope that this volume will continue to contribute to the growing interest in grammatical error detection by encouraging researchers to take a closer look at the field and its many challenging problems.

More and more historical texts are becoming available in digital form. Digitization of paper documents is motivated by the aim of preserving cultural heritage and making it more accessible, both to laypeople and scholars. As digital images cannot be searched for text, digitization projects increasingly strive to create digital text, which can be searched and otherwise automatically processed, in addition to facsimiles. Indeed, the emerging field of digital humanities heavily relies on the availability of digital text for its studies. Together with the increasing availability of historical texts in digital form, there is a growing interest in applying natural language processing (NLP) methods and tools to historical texts. However, the specific linguistic properties of historical texts -- the lack of standardized orthography, in particular -- pose special challenges for NLP. This book aims to give an introduction to NLP for historical texts and an overview of the state of the art in this field. The book starts with an overview of methods for the acquisition of historical texts (scanning and OCR), discusses text encoding and annotation schemes, and presents examples of corpora of historical texts in a variety of languages. The book then discusses specific methods, such as creating part-of-speech taggers for historical languages or handling spelling variation. A final chapter analyzes the relationship between NLP and the digital humanities. Certain recently emerging textual genres, such as SMS, social media, and chat messages, or newsgroup and forum postings share a number of properties with historical texts, for example, nonstandard orthography and grammar, and profuse use of abbreviations. The methods and techniques required for the effective processing of historical texts are thus also of interest for research in other domains. Table of Contents: Introduction / NLP and Digital Humanities / Spelling in Historical Texts / Acquiring Historical Texts / Text Encoding and Annotation Schemes / Handling Spelling Variation / NLP Tools for Historical Languages / Historical Corpora / Conclusion / Bibliography