Automated Speaking Assessment: Using Language Technologies to Score Spontaneous Speech provides a thorough overview of state-of-the-art automated speech scoring technology as it is currently used at Educational Testing Service (ETS). Its main focus is related to the automated scoring of spontaneous speech elicited by TOEFL iBT Speaking section items, but other applications of speech scoring, such as for more predictable spoken responses or responses provided in a dialogic setting, are also discussed. The book begins with an in-depth overview of the nascent field of automated speech scoring-its history, applications, and challenges-followed by a discussion of psychometric considerations for automated speech scoring. The second and third parts discuss the integral main components of an automated speech scoring system as well as the different types of automatically generated measures extracted by the system features related to evaluate the speaking construct of communicative competence as measured defined by the TOEFL iBT Speaking assessment. Finally, the last part of the book touches on more recent developments, such as providing more detailed feedback on test takers' spoken responses using speech features and scoring of dialogic speech. It concludes with a discussion, summary, and outlook on future developments in this area. Written with minimal technical details for the benefit of non-experts, this book is an ideal resource for graduate students in courses on Language Testing and Assessment as well as teachers and researchers in applied linguistics.

Fuzzy modeling usually comes with two contradictory requirements: interpretability, which is the capability to express the real system behavior in a comprehensible way, and accuracy, which is the capability to faithfully represent the real system. In this framework, one of the most important areas is linguistic fuzzy modeling, where the legibility of the obtained model is the main objective. This task is usually developed by means of linguistic (Mamdani) fuzzy rule-based systems. An active research area is oriented towards the use of new techniques and structures to extend the classical, rigid linguistic fuzzy modeling with the main aim of increasing its precision degree. Traditionally, this accuracy improvement has been carried out without considering the corresponding interpretability loss. Currently, new trends have been proposed trying to preserve the linguistic fuzzy model description power during the optimization process. Written by leading experts in the field, this volume collects some representative researcher that pursue this approach.

Franciska de Jong and Jan Landsbergen Jan Landsbergen 2 A compositional definition of the translation relation Jan Odijk 3 M-grammars Jan Landsbergen and Franciska de Jong 4 The translation process Lisette Appelo 5 The Rosetta characteristics Joep Rous and Harm Smit 6 Morphology Jan Odijk, Harm Smit and Petra de Wit 7 Dictionaries Jan Odijk 8 Syntactic rules Modular and controlled Lisette Appelo 9 M-grammars Compositionality and syntactic Jan Odijk 10 generalisations Jan Odijk and Elena Pinillos Bartolome 11 Incorporating theoretical linguistic insights Lisette Appelo 12 Divergences between languages Lisette Appelo 13 Categorial divergences Translation of temporal Lisette Appelo 14 expressions Andre Schenk 15 Idioms and complex predicates Lisette Appelo and Elly van Munster 16 Scope and negation Rene Leermakers and Jan Landsbergen 17 The formal definition of M-grammars Rene Leermakers and Joep Rous 18 An attribute grammar view Theo Janssen 19 An algebraic view Rene Leermakers 20 Software engineering aspects Jan Landsbergen 21 Conclusion Contents 1 1 Introduction 1. 1 Knowledge needed for translation . . . . . . . . . . . 2 1. 1. 1 Knowledge of language and world knowledge 2 1. 1. 2 Formalisation. . . . . . . . . . . . . . . . . 4 1. 1. 3 The underestimation of linguistic problems . 5 1. 1. 4 The notion of possible translation . 5 1. 2 Applications. . . . . . . . . . . 7 1. 3 A linguistic perspective on MT 9 1. 3. 1 Scope of the project 9 1. 3. 2 Scope of the book 11 1. 4 Organisation of the book . .

Over the last few decades, research on handwriting recognition has made impressive progress. The research and development on handwritten word recognition are to a large degree motivated by many application areas, such as automated postal address and code reading, data acquisition in banks, text-voice conversion, security, etc. As the prices of scanners, com puters and handwriting-input devices are falling steadily, we have seen an increased demand for handwriting recognition systems and software pack ages. Some commercial handwriting recognition systems are now available in the market. Current commercial systems have an impressive performance in recognizing machine-printed characters and neatly written texts. For in stance, High-Tech Solutions in Israel has developed several products for container ID recognition, car license plate recognition and package label recognition. Xerox in the U. S. has developed TextBridge for converting hardcopy documents into electronic document files. In spite of the impressive progress, there is still a significant perfor mance gap between the human and the machine in recognizing off-line unconstrained handwritten characters and words. The difficulties encoun tered in recognizing unconstrained handwritings are mainly caused by huge variations in writing styles and the overlapping and the interconnection of neighboring characters. Furthermore, many applications demand very high recognition accuracy and reliability. For example, in the banking sector, although automated teller machines (ATMs) and networked banking sys tems are now widely available, many transactions are still carried out in the form of cheques."

l This book evolved from the ARCADE evaluation exercise that started in 1995. The project's goal is to evaluate alignment systems for parallel texts, i. e., texts accompanied by their translation. Thirteen teams from various places around the world have participated so far and for the first time, some ten to fifteen years after the first alignment techniques were designed, the community has been able to get a clear picture of the behaviour of alignment systems. Several chapters in this book describe the details of competing systems, and the last chapter is devoted to the description of the evaluation protocol and results. The remaining chapters were especially commissioned from researchers who have been major figures in the field in recent years, in an attempt to address a wide range of topics that describe the state of the art in parallel text processing and use. As I recalled in the introduction, the Rosetta stone won eternal fame as the prototype of parallel texts, but such texts are probably almost as old as the invention of writing. Nowadays, parallel texts are electronic, and they are be coming an increasingly important resource for building the natural language processing tools needed in the "multilingual information society" that is cur rently emerging at an incredible speed. Applications are numerous, and they are expanding every day: multilingual lexicography and terminology, machine and human translation, cross-language information retrieval, language learning, etc."

One of the aims of Natural Language Processing is to facilitate .the use of computers by allowing their users to communicate in natural language. There are two important aspects to person-machine communication: understanding and generating. While natural language understanding has been a major focus of research, natural language generation is a relatively new and increasingly active field of research. This book presents an overview of the state of the art in natural language generation, describing both new results and directions for new research. The principal emphasis of natural language generation is not only to facili tate the use of computers but also to develop a computational theory of human language ability. In doing so, it is a tool for extending, clarifying and verifying theories that have been put forth in linguistics, psychology and sociology about how people communicate. A natural language generator will typically have access to a large body of knowledge from which to select information to present to users as well as numer of expressing it. Generating a text can thus be seen as a problem of ous ways decision-making under multiple constraints: constraints from the propositional knowledge at hand, from the linguistic tools available, from the communicative goals and intentions to be achieved, from the audience the text is aimed at and from the situation and past discourse. Researchers in generation try to identify the factors involved in this process and determine how best to represent the factors and their dependencies."

Corpus-based methods will be found at the heart of many language and speech processing systems. This book provides an in-depth introduction to these technologies through chapters describing basic statistical modeling techniques for language and speech, the use of Hidden Markov Models in continuous speech recognition, the development of dialogue systems, part-of-speech tagging and partial parsing, data-oriented parsing and n-gram language modeling. The book attempts to give both a clear overview of the main technologies used in language and speech processing, along with sufficient mathematics to understand the underlying principles. There is also an extensive bibliography to enable topics of interest to be pursued further. Overall, we believe that the book will give newcomers a solid introduction to the field and it will give existing practitioners a concise review of the principal technologies used in state-of-the-art language and speech processing systems. Corpus-Based Methods in Language and Speech Processing is an initiative of ELSNET, the European Network in Language and Speech. In its activities, ELSNET attaches great importance to the integration of language and speech, both in research and in education. The need for and the potential of this integration are well demonstrated by this publication.

This work is Volume II of a two-volume monograph on the theory of deterministic parsing of context-free grammars. Volume I, "Languages and Parsing" (Chapters 1 to 5), was an introduction to the basic concepts of formal language theory and context-free parsing. Volume II (Chapters 6 to 10) contains a thorough treat ment of the theory of the two most important deterministic parsing methods: LR(k) and LL(k) parsing. Volume II is a continuation of Volume I; together these two volumes form an integrated work, with chapters, theorems, lemmas, etc. numbered consecutively. Volume II begins with Chapter 6 in which the classical con structions pertaining to LR(k) parsing are presented. These include the canonical LR(k) parser, and its reduced variants such as the LALR(k) parser and the SLR(k) parser. The grammarclasses for which these parsers are deterministic are called LR(k) grammars, LALR(k) grammars and SLR(k) grammars; properties of these grammars are also investigated in Chapter 6. A great deal of attention is paid to the rigorous development of the theory: detailed mathematical proofs are provided for most of the results presented."

Parsing technology is concerned with finding syntactic structure in language. In parsing we have to deal with incomplete and not necessarily accurate formal descriptions of natural languages. Robustness and efficiency are among the main issuesin parsing. Corpora can be used to obtain frequency information about language use. This allows probabilistic parsing, an approach that aims at both robustness and efficiency increase. Approximation techniques, to be applied at the level of language description, parsing strategy, and syntactic representation, have the same objective. Approximation at the level of syntactic representation is also known as underspecification, a traditional technique to deal with syntactic ambiguity. In this book new parsing technologies are collected that aim at attacking the problems of robustness and efficiency by exactly these techniques: the design of probabilistic grammars and efficient probabilistic parsing algorithms, approximation techniques applied to grammars and parsers to increase parsing efficiency, and techniques for underspecification and the integration of semantic information in the syntactic analysis to deal with massive ambiguity. The book gives a state-of-the-art overview of current research and development in parsing technologies. In its chapters we see how probabilistic methods have entered the toolbox of computational linguistics in order to be applied in both parsing theory and parsing practice. The book is both a unique reference for researchers and an introduction to the field for interested graduate students.

Parallel and Distributed Information Systems brings together in one place important contributions and up-to-date research results in this fast moving area. Parallel and Distributed Information Systems serves as an excellent reference, providing insight into some of the most challenging research issues in the field.

This graduate-level text lays out the foundation of DSP for audio and the fundamentals of auditory perception, then goes on to discuss immersive audio rendering and synthesis, the digital equalization of room acoustics, and various DSP implementations. It covers a variety of topics and up-to-date results in immersive audio processing research: immersive audio synthesis and rendering, multichannel room equalization, audio selective signal cancellation, multirate signal processing for audio applications, surround sound processing, psychoacoustics and its incorporation in audio signal processing algorithms for solving various problems, and DSP implementations of audio processing algorithms on semiconductor devices.

This book includes a set of selected papers from the first "International Conference on Enterprise Information Systems," (ICEIS'99) held in SeUtbal, Portugal, from 27 to 30 March 1999. ICEIS focuses on real world applications and aims at becoming a major point of contact between research scientists, engineers and practitioners in the area of business applications of information systems. This year four simultaneous tracks were held, covering different aspects related to enterprise computing, including: Systems Analysis and Specijication, Database Technology and its Applications, Artijicial Intelligence and Decision Support Systems, and Internet and Intranet Computing. Although ICEIS'99 received more than 200 submissions, only 96 papers were accepted for oral presentation and only 24 were selected for inclusion in this book. These numbers demonstrate stringent quality criteria and the intention of maintaining a high quality forum for future editions ofthis conference. A number of additional keynote lectures, case studies and technical tutorials were also held. These presentations, by specialists in different knowledge areas made an important contribution to increase the overall quality of the Conference, and are partially expressed in the first two papers of the book."

The theory of formal languages is widely accepted as the backbone of t- oretical computer science. It mainly originated from mathematics (com- natorics, algebra, mathematical logic) and generative linguistics. Later, new specializations emerged from areas ofeither computer science(concurrent and distributed systems, computer graphics, arti?cial life), biology (plant devel- ment, molecular genetics), linguistics (parsing, text searching), or mathem- ics (cryptography). All human problem solving capabilities can be considered, in a certain sense, as a manipulation of symbols and structures composed by symbols, which is actually the stem of formal language theory. Language - in its two basic forms, natural and arti?cial - is a particular case of a symbol system. This wide range of motivations and inspirations explains the diverse - plicability of formal language theory ? and all these together explain the very large number of monographs and collective volumes dealing with formal language theory. In 2004 Springer-Verlag published the volume Formal Languages and - plications, edited by C. Martin-Vide, V. Mitrana and G. P?un in the series Studies in Fuzziness and Soft Computing 148, which was aimed at serving as an overall course-aid and self-study material especially for PhD students in formal language theory and applications. Actually, the volume emerged in such a context: it contains the core information from many of the lectures - livered to the students of the International PhD School in Formal Languages and Applications organized since 2002 by the Research Group on Mathem- ical Linguistics from Rovira i Virgili University, Tarragona, Spain."

This book covers content recognition in text, elaborating on past and current most successful algorithms and their application in a variety of settings: news filtering, mining of biomedical text, intelligence gathering, competitive intelligence, legal information searching, and processing of informal text. Today, there is considerable interest in integrating the results of information extraction in retrieval systems, because of the demand for search engines that return precise answers to flexible information queries.

Yorick Wilks is a central figure in the fields of Natural Language Processing and Artificial Intelligence. This book celebrates Wilks s career from the perspective of his peers in original chapters each of which analyses an aspect of his work and links it to current thinking in that area. This volume forms a two-part set together with Words and Intelligence I: Selected Works by Yorick Wilks, by the same editors."

This book is a revised version of my doctoral thesis which was submitted in April 1993. The main extension is a chapter on evaluation of the system de scribed in Chapter 8 as this is clearly an issue which was not treated in the original version. This required the collection of data, the development of a concept for diagnostic evaluation of linguistic word recognition systems and, of course, the actual evaluation of the system itself. The revisions made primarily concern the presentation of the latest version of the SILPA system described in an additional Subsection 8. 3, the development environment for SILPA in Sec tion 8. 4, the diagnostic evaluation of the system as an additional Chapter 9. Some updates are included in the discussion of phonology and computation in Chapter 2 and finite state techniques in computational phonology in Chapter 3. The thesis was designed primarily as a contribution to the area of compu tational phonology. However, it addresses issues which are relevant within the disciplines of general linguistics, computational linguistics and, in particular, speech technology, in providing a detailed declarative, computationally inter preted linguistic model for application in spoken language processing. Time Map Phonology is a novel, constraint-based approach based on a two-stage temporal interpretation of phonological categories as events."

A selection of papers presented at the international conference Applied Logic: Logic at Work', held in Amsterdam in December 1992. Nowadays, the term applied logic' has a very wide meaning, as numerous applications of logical methods in computer science, formal linguistics and other fields testify. Such applications are by no means restricted to the use of known logical techniques: at its best, applied logic involves a back-and-forth dialogue between logical theory and the problem domain. The papers focus on the application of logic to the study of natural language, in syntax, semantics and pragmatics, and the effect of these studies on the development of logic. In the last decade, the dynamic nature of natural language has been the most interesting challenge for logicians. Dynamic semantics is here applied to new topics, the dynamic approach is extended to syntax, and several methodological issues in dynamic semantics are systematically investigated. Other methodological issues in the formal studies of natural language are discussed, such as the need for types, modal operators and other logical operators in the formal framework. Further articles address the scope of these methodological issues from other perspectives ranging from cognition to computation. The volume presents papers that are interesting for graduate students and researchers in the field of logic, philosophy of language, formal semantics and pragmatics, and computational linguistics.

This book provides an overview of various techniques for the alignment of bitexts. It describes general concepts and strategies that can be applied to map corresponding parts in parallel documents on various levels of granularity. Bitexts are valuable linguistic resources for many different research fields and practical applications. The most predominant application is machine translation, in particular, statistical machine translation. However, there are various other threads that can be followed which may be supported by the rich linguistic knowledge implicitly stored in parallel resources. Bitexts have been explored in lexicography, word sense disambiguation, terminology extraction, computer-aided language learning and translation studies to name just a few. The book covers the essential tasks that have to be carried out when building parallel corpora starting from the collection of translated documents up to sub-sentential alignments. In particular, it describes various approaches to document alignment, sentence alignment, word alignment and tree structure alignment. It also includes a list of resources and a comprehensive review of the literature on alignment techniques. Table of Contents: Introduction / Basic Concepts and Terminology / Building Parallel Corpora / Sentence Alignment / Word Alignment / Phrase and Tree Alignment / Concluding Remarks

A history of machine translation (MT) from the point of view of a major writer and innovator in the field is the subject of this book. It details the deep differences between rival groups on how best to do MT, and presents a global perspective covering historical and contemporary systems in Europe, the US and Japan. The author considers MT as a fundamental part of Artificial Intelligence and the ultimate test-bed for all computational linguistics.

In 1992 it seemed very difficult to answer the question whether it would be possible to develop a portable system for the automatic recognition and translation of spon taneous speech. Previous research work on speech processing had focused on read speech only and international projects aimed at automated text translation had just been terminated without achieving their objectives. Within this context, the German Federal Ministry of Education and Research (BMBF) made a careful analysis of all national and international research projects conducted in the field of speech and language technology before deciding to launch an eight-year basic-research lead project in which research groups were to cooperate in an interdisciplinary and international effort covering the disciplines of computer science, computational linguistics, translation science, signal processing, communi cation science and artificial intelligence. At some point, the project comprised up to 135 work packages with up to 33 research groups working on these packages. The project was controlled by means of a network plan. Every two years the project sit uation was assessed and the project goals were updated. An international scientific advisory board provided advice for BMBF. A new scientific approach was chosen for this project: coping with the com plexity of spontaneous speech with all its pertinent phenomena such as ambiguities, self-corrections, hesitations and disfluencies took precedence over the intended lex icon size. Another important aspect was that prosodic information was exploited at all processing stages."

Most of the books about computational (lexical) semantic lexicons deal with the depth (or content) aspect of lexicons, ignoring the breadth (or coverage) aspect. This book presents a first attempt in the community to address both issues: content and coverage of computational semantic lexicons, in a thorough manner. Moreover, it addresses issues which have not yet been tackled in implemented systems such as the application time of lexical rules. Lexical rules and lexical underspecification are also contrasted in implemented systems. The main approaches in the field of computational (lexical) semantics are represented in the present book (including Wordnet, CyC, Mikrokosmos, Generative Lexicon). This book embraces several fields (and subfields) as different as: linguistics (theoretical, computational, semantics, pragmatics), psycholinguistics, cognitive science, computer science, artificial intelligence, knowledge representation, statistics and natural language processing. The book also constitutes a very good introduction to the state of the art in computational semantic lexicons of the late 1990s.

The last decade has been one of dramatic progress in the field of Natural Language Processing (NLP). This hitherto largely academic discipline has found itself at the center of an information revolution ushered in by the Internet age, as demand for human-computer communication and informa tion access has exploded. Emerging applications in computer-assisted infor mation production and dissemination, automated understanding of news, understanding of spoken language, and processing of foreign languages have given impetus to research that resulted in a new generation of robust tools, systems, and commercial products. Well-positioned government research funding, particularly in the U. S., has helped to advance the state-of-the art at an unprecedented pace, in no small measure thanks to the rigorous 1 evaluations. This volume focuses on the use of Natural Language Processing in In formation Retrieval (IR), an area of science and technology that deals with cataloging, categorization, classification, and search of large amounts of information, particularly in textual form. An outcome of an information retrieval process is usually a set of documents containing information on a given topic, and may consist of newspaper-like articles, memos, reports of any kind, entire books, as well as annotated image and sound files. Since we assume that the information is primarily encoded as text, IR is also a natural language processing problem: in order to decide if a document is relevant to a given information need, one needs to be able to understand its content."

Before designing a speech application system, three key questions have to be answered: who will use it, why and how often? This book focuses on these high-level questions and gives a criteria of when and how to design speech systems. After an introduction, the state-of-the-art in modern voice user interfaces is displayed. The book goes on to evolve criteria for designing and evaluating successful voice user interfaces. Trends in this fast growing area are also presented.

Among all information systems that are nowadays available, web sites are definitely the ones having the widest potential audience and the most significant impact on the everyday life of people. Web sites contribute largely to the information society: they provide visitors with a large array of services and information and allow them to perform various tasks without prior assumptions about their computer literacy. Web sites are assumed to be accessible and usable to the widest possible audience. Consequently, usability has been recognized as a critical success factor for web sites of every kind. Beyond this universal recognition, usability still remains a notion that is hard to grasp. Summative evaluation methods have been introduced to identify potential usability problems to assess the quality of web sites. However, summative evaluation remains limited in impact as it does not necessarily deliver constructive comments to web site designers and developers on how to solve the usability problems. Formative evaluation methods have been introduced to address this issue. Evaluation remains a process that is hard to drive and perform, while its potential impact is probably maximal for the benefit of the final user. This complexity is exacerbated when web sites are very large, potentially up to several hundreds of thousands of pages, thus leading to a situation where eval uating the web site is almost impossible to conduct manually. Therefore, many attempts have been made to support evaluation with: * Models that capture some characteristics of the web site of interest.

A big amount of important, 'economically relevant' information, is buried within the huge mass of multimedia documents that correspond to some form of 'narrative' description.

Due to the ubiquity of these 'narrative' resources, being able to represent in a general, accurate, and effective way their semantic content - i.e., their key 'meaning' - is then both conceptually relevant and economically important. In this book, we present the main properties of NKRL ('Narrative Knowledge Representation Language'), a language expressly designed for representing, in a standardised way, the 'meaning' of complex multimedia narrative documents. NKRL is a fully implemented language/environment. The software exists in two versions, an ORACLE-supported version and a file-oriented one.

Written from a multidisciplinary perspective, this exhaustive description of NKRL and of the associated knowledge representation principles will be an invaluable source of reference for practitioners, researchers, and graduates.