This book concerns non-linguistic knowledge required to perform computational natural language understanding (NLU). The main objective of the book is to show that inference-based NLU has the potential for practical large scale applications. First, an introduction to research areas relevant for NLU is given. We review approaches to linguistic meaning, explore knowledge resources, describe semantic parsers, and compare two main forms of inference: deduction and abduction. In the main part of the book, we propose an integrative knowledge base combining lexical-semantic, ontological, and distributional knowledge. A particular attention is payed to ensuring its consistency. We then design a reasoning procedure able to make use of the large scale knowledge base. We experiment both with a deduction-based NLU system and with an abductive reasoner. For evaluation, we use three different NLU tasks: recognizing textual entailment, semantic role labeling, and interpretation of noun dependencies.

Although there has been much progress in developing theories, models and systems in the areas of Natural Language Processing (NLP) and Vision Processing (VP), there has heretofore been little progress on integrating these two subareas of Artificial Intelligence (AI). This book contains a set of edited papers addressing theoretical issues and the grounding of representations in NLP and VP from philosophical and psychological points of view. The papers focus on site descriptions such as the reasoning work on space at Leeds, UK, the systems work of the ILS (Illinois, U.S.A.) and philosophical work on grounding at Torino, Italy, on Schank's earlier work on pragmatics and meaning incorporated into hypermedia teaching systems, Wilks' visions on metaphor, on experimental data for how people fuse language and vision and theories and computational models, mainly connectionist, for tackling Searle's Chinese Room Problem and Harnad's Symbol Grounding Problem. The Irish Room is introduced as a mechanism through which integration solves the Chinese Room. The U.S.A., China and the EU are well reflected, showing the fact that integration is a truly international issue. There is no doubt that all of this will be necessary for the SuperInformationHighways of the future.

Written by leading international experts, this volume presents contributions establishing the feasibility of human language-like communication with robots. The book explores the use of language games for structuring situated dialogues in which contextualized language communication and language acquisition can take place. Within the text are integrated experiments demonstrating the extensive research which targets artificial language evolution. Language Grounding in Robots uses the design layers necessary to create a fully operational communicating robot as a framework for the text, focusing on the following areas: Embodiment; Behavior; Perception and Action; Conceptualization; Language Processing; Whole Systems Experiments. This book serves as an excellent reference for researchers interested in further study of artificial language evolution.

It is becoming crucial to accurately estimate and monitor speech quality in various ambient environments to guarantee high quality speech communication. This practical hands-on book shows speech intelligibility measurement methods so that the readers can start measuring or estimating speech intelligibility of their own system. The book also introduces subjective and objective speech quality measures, and describes in detail speech intelligibility measurement methods. It introduces a diagnostic rhyme test which uses rhyming word-pairs, and includes: An investigation into the effect of word familiarity on speech intelligibility. Speech intelligibility measurement of localized speech in virtual 3-D acoustic space using the rhyme test. Estimation of speech intelligibility using objective measures, including the ITU standard PESQ measures, and automatic speech recognizers.

When individuals read or listen to prose they try to understand what it means. This is quite obvious. However, the cognitive mechanisms that participate in prose comprehension are far from obvious. Even simple stories involve com plexities that have stymied many cognitive scientists. Why is prose comprehen sion so difficult to study? Perhaps because comprehension is guided by so many domains of knowledge. Perhaps because some critical mysteries of prose comprehension reside between the lines-in the mind of the comprehender. Ten years ago very few psychologists were willing to dig beyond the surface of explicit code in their studies of discourse processing. Tacit knowledge, world knowledge, inferences, and expectations were slippery notions that experimental psychologists managed to circumvent rather than understand. In many scientific circles it was taboo to investigate mechanisms and phenomena that are not directly governed by the physical stimulus. Fortunately, times have changed. Cognitive scientists are now vigorously exploring the puzzles of comprehension that lie beyond the word. The study of discourse processing is currently growing at a frenetic pace."

Summary his book was written primarily for people who intend or wish to develop new machines for the output of typefaces. It is practical to categorize equipment into three groups for which digital alphabets are required - 1) display devices, 2) typesetting machines and 3) numerically controlled (NC) machines. Until now, development of typefaces has been overly dependent upon the design of the respective machine on which it was to be used. This need not be the case. Digitization of type should be undertaken in two steps: the preparation of a database using hand-digitization, and the subsequent automatic generation of machine formats by soft scanning, through the use of a computer-based program. Digital formats for typefaces are ideally suited to system atic ordering, as are coding techniques. In this volume, various formats are investigated, their properties discussed and rela tive production requirements analyzed. Appendices provide readers additional information, largely on digital formats for typeface storage introduced by the IKARUS system. This book was composed in Latino type, developed by Hermann Zapf from his Melior for URW in 1990. Compo sition was accomplished on a Linotronic 300, as well as on an Agfa 9400 typesetter using PostScript. v Preface Preface his book was brought out by URW Publishers in 1986 with the title "Digital Formats for Typefaces;). It was translated into English in 1987, Japanese in 1989 and French in 1991.

8. 5 Summary In this chapter we have identified three basic patterns of influences that lead to ambiguity in the QP analysis of the basic active furnace state. We have then shown how modification of these patterns, by adding equilibrium values and sensitivity annotations on influence arcs, could permit resolu tion of the ambiguities. Finally, we have described in detail the extensions needed to the basic influence resolution algorithm in QP theory to oper ate on these extended descriptions. We have also shown that the modified influence resolution algorithm corrects an error in Forbus' original method for combining influences. We have then presented an extended example in which introduction of equilibrium assumptions eliminates all ambigu ity in the influence resolution deduction. In the next chapter we extend these techniques further, by developing a qualitative perturbation analysis technique that permits us to answer "what ir' control questions; then we extend this technique to obtain quantitative, as well as qualitative, effects of hypothetical control actions. 8."

It is an established tradition that researchers from many countries get together on the average every three years for a two week Advanced Studies Institute on Automatic Speech Recognition and Synthesis. According to ASI policies the Institute is financed by NATO. This book contains the texts of lectures and papers contributed by the attendees of the ASI which was held July 2 - 14, 1984, at Bonas, Gers, France. Focussed on New Systems and Architectures for Automatic Speech Recognition and Synthesis, this book is divided into 4 parts: (a) Review of ba8ic algorithm8 (b) SY8tem architecture and VLSI for automatic Speech (c) Software 8Y8tem8 for automatic 8peech recognition, (d) Speech 8ynthe8i8 and phonetic8. Due to the international nature of the Institute, the readers will find in this book different styles, different points of view and applications to different languages. This reflects also some characteristics of the International Association for Pattern Recognition ( APR) whose technical committee on Speech Recognition has organized this ASI. Proposed contributions have been reviewed by an Editorial Committee composed of W. Ainsworth (Kent), R. Bisiani (Pittsburgh), J. P. Haton (Nancy), W. Hess (Munich), J. L. Houle (Montreal), P. Laface (Turin), R. Moore (Malvern), H. Niemann (Erlangen) and J. Ohala (Berkeley). Typesetting of the book was performed using SYMSET facilities developed entirely by the Department of Computer Science at Concordia University. Special thanks are due to L. Lam, H. Monkiewicz and L. Thiel.

We are living in a multilingual world and the diversity in languages which are used to interact with information access systems has generated a wide variety of challenges to be addressed by computer and information scientists. The growing amount of non-English information accessible globally and the increased worldwide exposure of enterprises also necessitates the adaptation of Information Retrieval (IR) methods to new, multilingual settings.

Peters, Braschler and Clough present a comprehensive description of the technologies involved in designing and developing systems for Multilingual Information Retrieval (MLIR). They provide readers with broad coverage of the various issues involved in creating systems to make accessible digitally stored materials regardless of the language(s) they are written in. Details on Cross-Language Information Retrieval (CLIR) are also covered that help readers to understand how to develop retrieval systems that cross language boundaries. Their work is divided into six chapters and accompanies the reader step-by-step through the various stages involved in building, using and evaluating MLIR systems. The book concludes with some examples of recent applications that utilise MLIR technologies. Some of the techniques described have recently started to appear in commercial search systems, while others have the potential to be part of future incarnations.

The book is intended for graduate students, scholars, and practitioners with a basic understanding of classical text retrieval methods. It offers guidelines and information on all aspects that need to be taken into consideration when building MLIR systems, while avoiding too many 'hands-on details' that could rapidly become obsolete. Thus it bridges the gap between the material covered by most of the classical IR textbooks and the novel requirements related to the acquisition and dissemination of information in whatever language it is stored.

This book is based on the NATO Advanced Research Workshop on Structures of Com munication and Intelligent Help for Hypermedia Courseware, which was held at Espinho, Portugal, April 19-24, 1990. The texts included here should not be regarded as untouched proceedings of this meeting, but as the result of the reflections which took place there and which led the authors to revise their texts in that light. The Espinho ARW was itself to some extent the continuation of the ARW on Designing Hypermedia/Hypertext for Learning, held in Germany in 1989 (D. H. Jonassen, H. Mandl (eds.): Designing Hypermedia for Learning. NATO ASI Series F, Vol. 67. Springer 1990). At that meeting an essential conclusion becarne apparent: the importance and interest of hyper media products as potential pedagogical tools. It was then already predictable that the enormous evolution of hypermedia would lead to its association with multimedia technologies, namely for the production of courseware. Parallel to the improvement of the didactic potential and quality which results from this association, it nevertheless brought along a natural array of difficulties, some old, some new, in the con ception and use of hypermedia products. Today there is agreement that one of the most promising technological advances for education is represented by the use of text, sound and images based on nonlinear techniques of information handling and searching of hypermedia architectures. The problem of hypermedia is fundamentally one of communication; this leads to an attempt at defining a language for hypermedia.

The present book is based on the conference Software Development and Reality Construction held at SchloB Eringerfeld in Germany, September 25 - 30, 1988. This was organized by the Technical University of Berlin (TUB) in cooperation with the German National Research Center for Computer Science (GMD), Sankt Augustin, and sponsored by the Volkswagen Foundation whose financial support we gratefully acknowledge. The conference was an interdisciplinary scientific and cultural event aimed at promoting discussion on the nature of computer science as a scientific discipline and on the theoretical foundations and systemic practice required for human-oriented system design. In keeping with the conversational style of the conference, the book comprises a series of individual contributions, arranged so as to form a coherent whole. Some authors reflect on their practice in computer science and system design. Others start from approaches developed in the humanities and the social sciences for understanding human learning and creativity, individual and cooperative work, and the interrelation between technology and organizations. Thus, each contribution makes its specific point and can be read on its own merit. But, at the same time, it takes its place as a chapter in the book, along with all the other contributions, to give what seemed to us a meaningful overall line of argumentation. This required careful editorial coordination, and we are grateful to all the authors for bearing with us throughout the slow genesis of the book and for complying with our requests for extensive revision of some of the manuscripts.

Keith M. Ponting Speech Research Unit, DERA Malvern St. Andrew's Road, Great Malvern, Worcs. WR14 3PS, UK email: ponting

This book is the final product of a conference organized at the Free Univer- sity, Amsterdam, by some members of the Dutch Human Performance Group and sponsored by the Dutch Psychonomic Society. We first of all thank the Society for financially supporting this publication, and the Free University for providing technical support. P.J.G. Keuss, A.A.J. Mannaerts, and W. Hulstijn, members of the organizing commitee, and J.A. Michon and W. Molenaar collaborated with the editors in defining the fields dealt with at the conference and in the book and in getting together the team of authors. All the chapters in this volume have been reviewed by a team of external referees, who generously spent their time to improve the readability, coher- ence, and scientific standard of the work as a whole: H. Bogers, Institute for Experimental Psychology, University of Groningen, The Netherlands; P. Innocent, Leicester Polytechnic, UK; G.A.M. Kempen, Institute for Cogni- tion Research and Information Technology, Nijmegen, The Netherlands; J. Moraal, Institute for Perception RVO/TNO, Soesterberg, The Netherlands; I.M. van Oorschot, Department of Economics, Free University, Amsterdam, The Netherlands; G.R.E. Ouweneel, Institute for Experimental Psychology, Haren, The Netherlands; J.G.W. Raaymakers, Institute for Perception RVO/TNO, Soesterberg, The Netherlands; G. Rohr, IBM Science Center, Heidelberg, FRG; M.J. Tauber, Department of Computer Science, University of Paderborn, FRG; Y. Waern, Department of Psychology, University of Stockholm, Sweden; G. d'Ydewalle, Department of Psychology, University of Leuven, Belgium.

The papers in this book are the result of the NATO conference "Cognitive Modelling and Inter active Environments" that was held in Mierlo, the Netherlands, November 5 - 8, 1990. Within the framework of the NATO Advanced Research Workshops this invitational conference was naturally on learning, but it emphasized a number of factors that are not generally treated in dis cussions on learning and specifically in computer-assisted learning. It was realized by the orig inators of the conference that, with respect to computer-assisted instruction, the stage has not nearly been reached where it is well known how a successful interactive instructional environ ment has to be created. This contrasts strongly with the sheer number of computerized learning programs that exist already and continue to be produced. Frequently the motivation to create a computer-assisted learning program is heavily connected with a scientific discipline. Logically it is the proper task for instructional science to produce instructional programs. The high degree of formalization in linguistics allows one often in a straightforward way, to au tomate learning programs for language instruction. Artificial intelligence, in its endeavour to capture basic principles of knowledge representation and knowledge acquisition, leads naturally to Intelligent Tutoring Systems. Computer science is the logical breeding ground for programs that manipulate knowledge for many different students, that register actions reliably, and that automate parts of time-intensive teaching tasks. The joint concern of all of these approaches is the transfer of knowledge.

Computers have changed typography and prepress as well as printing. Typefaces are manufactured by "digital punch cutters" with a PC, not any more by punch cutters. Typefaces are constructed an output by a new technolgy, the so-called fonttechnology. The book by Peter Karow covers the whole area of it. It offers various chapters about (among others) issues like intelligent font scaling, kerning, quality of type, legibility, and problems of different output devices. It is interesting to read about Gutenberg setting, the font market, optical scaling, and last but not least a "hand on" Kanjhi, the Chinese/Japanese Glyphs. Furthermore, Fonttechnology contains a number of valuable and instructive appendices. Almost everything one has to know about type and computers!

This book constitutes the refereed proceedings of the 8th Discourse Anaphora and Anaphor Resolution Colloquium, DAARC 2011, held in Faro, Portugal, in October 2011. The 16 revised full papers presented were carefully reviewed and selected from 45 initial submissions. The papers are organized in topical sections on computational resolution methodology and systems; language analysis and representation; and human processing and performance.

This volume in the Basic Research Series consists of the proceedings of the Symposium on Natural Language and Speech held during the ESPRIT Conference of November 1991 - a conference that serves to open up ESPRIT results not only to the ESPRIT community but also to the entire European IT industry and its users. The symposium is organised by the newly launched Network of Excellence on Language and Speech (3701) which brings together the foremost European experts and institutions in these two domains. By bringing together these two communities, which have so far been working in relative isolation from each other, the network aims to augment the focusing of research onto the long-term goal of the "construction of an integrated model of the cognitive chain linking speech to reasoning via natural language." To advance towards this industrially significant goal, the network operates at different levels - a strategy for research, a coordination for the training of needed researchers and a coordination of the use of its resource and communication infrastructure for the most efficient interworking of the members of the community who are spread all over Europe. This symposium is a small but significant building block for the achievement of the goals of the network.

In 1989, the ISO Standard 8613 "Office Document Architecture (ODA) and Interchange Format" was published. The Standard is intended for the interchange of documents in an Open Systems environment. ISO 8613 is technically identical to the CCITT Recommendations of the T.410 series called "Open Document Architecture (ODA) and Interchange Format" published in 1988. Almost all major companies in the office automation and telecommunication area are currently developing products based on this Standard. In this book, all important aspects of the presently publishedeight parts of the Standard are discussed. The book provides a comprehensiveand detailed introduction to the technical specifications of ISO 8613 and the concepts on which these specifications are based, including the extensions which were added to the ODA Standard in 1991. The book isprimarily addressed to readers who want to investigate the applicability of the Standard for their document interchange problems, plan to acquire products based on the Standard, or intend to develop document processingsystems conforming to the Standard.

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

As its title suggests, "Uncertainty Management in Information Systems" is a book about how information systems can be made to manage information permeated with uncertainty. This subject is at the intersection of two areas of knowledge: information systems is an area that concentrates on the design of practical systems that can store and retrieve information; uncertainty modeling is an area in artificial intelligence concerned with accurate representation of uncertain information and with inference and decision-making under conditions infused with uncertainty. New applications of information systems require stronger capabilities in the area of uncertainty management. Our hope is that lasting interaction between these two areas would facilitate a new generation of information systems that will be capable of servicing these applications. Although there are researchers in information systems who have addressed themselves to issues of uncertainty, as well as researchers in uncertainty modeling who have considered the pragmatic demands and constraints of information systems, to a large extent there has been only limited interaction between these two areas. As the subtitle, "From Needs to Solutions," indicates, this book presents view points of information systems experts on the needs that challenge the uncer tainty capabilities of present information systems, and it provides a forum to researchers in uncertainty modeling to describe models and systems that can address these needs."

This book contains the reports of selected projects involving natural language commu nication with pictorial information systems. More than just a record of research results, however, it presents concrete applications to the solution of a wide variety of problems. The authors are all prominent figures in the field whose authoritative contributions help ensure its continued expansion in both size and significance. Y. C. Lee and K S. Fu (Purdue University, USA) survey picture query languages which form an interface between the pictorial database system and the user and support infor mation retrieval, data entry and manipulation, data analysis and output generation. They include explicit picture query languages that augment alphanumeric data query langua ges as well as languages and command sets which are implicitly embedded in a pictorial information system but perform similar functions. It is worth mentioning that some forms of query languages can be transformed from a given set of natural language senten ces by using ATN (Augmented Transition Networks), which consequently allows for na turallanguage communication with information system."

User models have recently attracted much research interest in the field of artificial intelligence dialog systems. It has become evident that a flexible user-oriented dialog behavior of such systems can be realized only if the system disposes of a model of the user, containing assumptions about the users background knowledge as well as the users goals and plans in consulting the system. Research in the field of user models investigates how such assumptions can be automatically created, represented and exploited by the system in the course of an interaction with the user. This volume is the first survey pertaining to the field of user modeling. Most of the prominent international researchers in this area have contributed to this volume. Their papers are grouped into four sections: The introductory section contains a general view of the field as a whole, and a number of surveys of specific problems and techniques in user modeling. Sections two and three describe eight user modeling systems, with the focus lying on the automatic creation and exploitation of assumptions about the user respectively. The final section discusses several limits of current systems, and proposes solutions as to how some of the shortcomings might be overcome. In order to increase the quality and the coherency of the volume, each paper has been reviewed by all other contributors. Cross-references have been integrated wherever appropriate. All contributions are introduced in editorial prefaces pertaining to each section. A subject index and an extensive bibliography supplement the book.

The past decade has seen a revolution in the field of spoken dialogue systems. As in other areas of Computer Science and Artificial Intelligence, data-driven methods are now being used to drive new methodologies for system development and evaluation. This book is a unique contribution to that ongoing change. A new methodology for developing spoken dialogue systems is described in detail. The journey starts and ends with human behaviour in interaction, and explores methods for learning from the data, for building simulation environments for training and testing systems, and for evaluating the results. The detailed material covers: Spoken and Multimodal dialogue systems, Wizard-of-Oz data collection, User Simulation methods, Reinforcement Learning, and Evaluation methodologies. The book is a research guide for students and researchers with a background in Computer Science, AI, or Machine Learning. It navigates through a detailed case study in data-driven methods for development and evaluation of spoken dialogue systems. Common challenges associated with this approach are discussed and example solutions are provided. This work provides insights, lessons, and inspiration for future research and development - not only for spoken dialogue systems in particular, but for data-driven approaches to human-machine interaction in general.

The growing efficiency and lower prices of computers make it possible to apply them more widely in the economy. However, the wide use of computers in every day life is hindered by a number of factors which constitute what we shall call the "problem of contact" or of "talking." The difficulty is that languages used by computers differ substantially from users' languages and are not understood by specialists who are unfamiliar with programming. This is why those specialists who use computers need the help of programmers to communicate. Since this form of communication has many more or less obvious shortcomings, great efforts have been made to find a solution to the problem of contact. Two ap proaches can be distinguished here: (1) making the computer language similar to the natural language; (2) making the user's language resemble that of computers through formalizing the former. This book deals with the first approach. We shall consider those systems which make it possible to "talk" with the user in limited natural language (LNL). The term "natural language" (NL) has been used in the title of this book instead of LNL. The reason for not using the term "limited natural language" is that this term has two meanings: (1) a dialect of a natural language; (2) a formal language whose operators are expressed by words taken from a natural language (e. g."

The design of formal calculi in which fundamental concepts underlying interactive systems can be described and studied has been a central theme of theoretical computer science in recent decades, while membrane computing, a rule-based formalism inspired by biological cells, is a more recent field that belongs to the general area of natural computing. This is the first book to establish a link between these two research directions while treating mobility as the central topic. In the first chapter the authors offer a formal description of mobility in process calculi, noting the entities that move: links ( -calculus), ambients (ambient calculi) and branes (brane calculi). In the second chapter they study mobility in the framework of natural computing. The authors define several systems of mobile membranes in which the movement inside a spatial structure is provided by rules inspired by endocytosis and exocytosis. They study their computational power in comparison with the classical notion of Turing computability and their efficiency in algorithmically solving hard problems in polynomial time. The final chapter deals with encodings, establishing links between process calculi and membrane computing so that researchers can share techniques between these fields. The book is suitable for computer scientists working in concurrency and in biologically inspired formalisms, and also for mathematically inclined scientists interested in formalizing moving agents and biological phenomena. The text is supported with examples and exercises, so it can also be used for courses on these topics.