The ?fth campaign of the Cross-Language Evaluation Forum (CLEF) for Eu- pean languages was held from January to September 2004. Participation in the CLEF campaigns has increased each year and CLEF 2004 was no exception: 55 groups submitted results for one or more of the di?erent tracks compared with 42 groups in the previous year. CLEF 2004 also marked a breaking point with respect to previous campaigns. The focus was no longer mainly concentrated on multilingual document retrieval as in previous years but was diversi?ed to include di?erent kinds of text retrieval across languages (e. g. , exact answers in the question-answering track) and retrieval on di?erent kinds of media (i. e. , not just plain text but collections containing image and speech as well). In ad- tion, increasing attention was given to issues that regard system usability and user satisfaction with tasks to measure the e?ectiveness of interactive systems or system components being included in both the cross-language question - swering and image retrieval tasks with the collaboration of the coordinators of the interactive track. The campaign culminated in a two-and-a-half-day workshop held in Bath, UK, 15-17 September, immediately following the 8th European Conference on Digital Libraries. The workshop was attended by nearly 100 researchers and s- tem developers.

This volume contains the ?nal proceedings of the 2004 Metainformatics Sym- sium (MIS 2004). The event was held during 15-18 September 2004 in Salzburg, Austria at Salzburg Research. MIS is an annual event focusing on ?nding common ground shared by - searchers and practitioners in many di?erent computer science areas who may use similar methods to achieve di?erent ends. The goal is to ?nd useful abstr- tions, notations, analytical frameworks, formalisms, and systems that improve ourunderstandingoftheunderlyingstructuresofvariousdisciplinesandfamilies of systems within computer science. Ideally these constructs should have usef- ness in conveying knowledge and understanding across disciplinary boundaries. The proceedings of previous MIS events were also published by Springer in the Lecture Notes in Computer Science series: LNCS 3002 (2003), LNCS 2641 (2002), LNCS 2266 (2001), and LNCS 1903 (2000). As with previous events in the MIS series, MIS 2004 attracted quality papers and brought together researchers from many di?erent ?elds within computer s- ence.WeexperiencedinterestingpresentationsandlivelydiscussionsinSalzburg. I hope that you will ?nd the papers contained in this volume as interesting as the other members of the Program Committee and I have. This volume would not have been possible without the help and assistance of many people. In particular, I would like to acknowledge the assistance of the Springereditors, AnnaKramerandChristineGun ] ther, andtheExecutiveEditor of the LNCS series, Alfred Hofmann.

Refereed postproceedings of the International Conference on Non-Linear Speech Processing, NOLISP 2005. The 30 revised full papers presented together with one keynote speech and 2 invited talks were carefully reviewed and selected from numerous submissions for inclusion in the book. The papers are organized in topical sections on speaker recognition, speech analysis, voice pathologies, speech recognition, speech enhancement, and applications.

The 16th Annual Symposium on Combinatorial Pattern Matching was held on Jeju Island, Korea on June 19-22, 2005. Previous meetings were held in Paris, London, Tucson, Padova, Asilomar, Helsinki, Laguna Beach, Aarhus, Piscataway, Warwick, Montreal, Jerusalem, Fukuoka, Morelia, and Istanbul over the years 1990-2004. In response to the call for papers, CPM 2005 received a record number of 129papers.Eachsubmissionwasreviewedbyatleast threeProgramCommittee members with the assistance of external referees. Since there were many hi- quality papers, the Program Committee's task was extremely di?cult. Through an extensive discussion the Program Committee accepted 37 of the submissions tobepresentedattheconference.Theyconstituteoriginalresearchcontributions in combinatorial pattern matching and its applications. Inadditiontotheselectedpapers, CPM2005hadthreeinvitedpresentations, by Esko Ukkonen from the University of Helsinki, Ming Li from the University of Waterloo, and Naftali Tishby from The Hebrew University of Jerusalem. We would like to thank all Program Committee members and external r- erees for their excellent work, especially given the demanding time constraints; they gave the conference its distinctive character. We also thank all who s- mitted papers for consideration; they all contributed to the high quality of the conference. Finally, we thank the Organizing Committee members and the graduates- dents who worked hard to put in place the logistical arrangements of the c- ference. It is their dedicated contribution that made the conference possible and enjoyable

This volume contains invited and contributed papers presented at the 9th International Summer School "Neural Nets E.R. Caianiello" on Nonlinear Speech Processing: Al- rithms and Analysis, held in Vietri sul Mare, Salerno, Italy, during September 13-18, 2004. The aim of this book is to provide primarily high-level tutorial coverage of the ?elds related to nonlinear methods for speech processing and analysis, including new approaches aimed at improving speech applications. Fourteen surveys are offered by specialists in the ?eld. Consequently, the volume may be used as a reference book on nonlinear methods for speech processing and an- ysis. Also included are ?fteen papers that present original contributions in the ?eld and complete the tutorials. The volume is divided into ?ve sections: Dealing with Nonlinearities in Speech S- nal, Acoustic-to-Articulatory Modeling of Speech Phenomena, Data Driven and Speech Processing Algorithms, Algorithms and Models Based on Speech Perception Mec- nisms, and Task-Oriented Speech Applications. Dealing with Nonlinearities in Speech Signals is an introductory section where n- linear aspects of the speech signal are introduced from three different points of view. The section includes three papers. The ?rst paper, authored by Anna Esposito and Maria Marinaro, is an attempt to introduce the concept of nonlinearity revising several nonl- ear phenomena observed in the acoustics, the production and the perception of speech. Also discussed is the engineering endeavor to model these phenomena.

Edited in collaboration with FoLLI, the Association of Logic, Language and Information, this book inaugurates the new FoLLI LNAI subline. It constitutes the refereed proceedings of the 5th International Conference on Logical Aspects of Computational Linguistics, LACL 2005, held in Bordeaux, France in April 2005.

The 25 revised full papers presented were carefully reviewed and selected from over 40 submissions. The papers address a wide range of logical and formal methods in computational linguistics with studies of particular grammar formalisms and their computational properties, language engineering, and traditional topics about the syntax/semantics interface.

Welcome to Santiago de Compostela! We are pleased to host the 27th Annual EuropeanConferenceonInformationRetrievalResearch(ECIR2005)onits?rst visit to Spain. These proceedings contain the refereed full papers and poster abstracts p- sented at ECIR 2005. This conference was initially established by the Infor- tion Retrieval Specialist Group of the British Computer Society (BCS-IRSG) under the name "Annual Colloquium on Information Retrieval Research. " The colloquium was held in the United Kingdom each year until 1998, when the event was organized in Grenoble, France. Since then the conference venue has alternated between the United Kingdom and Continental Europe, re?ecting the growing European orientation of ECIR. For the same reason, in 2001 the event was renamed "European Conference on Information Retrieval Research. " In - cent years, ECIR has continued to grow and has become the major European forum for the discussion of research in the ?eld of information retrieval. ECIR 2005 was held at the Technical School of Engineering of the University of Santiago de Compostela, Spain. In terms of submissions, ECIR 2005 was a record-breaking success, since 124 full papers were submitted in response to the call for papers. This was a sharp increase from the 101 submissions received for ECIR 2003, which was the most successful ECIR in terms of submissions. ECIR 2005 established also a call for posters, and 41 posters where submitted. Paper and poster submissions were received from across Europe and further a?eld, including North America, South America, Asia and Australia, which is a clear indicationofthegrowingpopularityandreputationoftheconference.

Spoken dialog systems allow people to get information, conduct business, and be entertained, simply by speaking to a computer. There are hundreds of these systems currently in use, handling millions of interactions every day. How do they work? What problems do they solve? The goal of this book is to answer these questions and others like them, including:

How can I decide if a spoken dialog system is a good fit for the needs of my organization?

Whata (TM)s the difference between a voice user interface and a conventional graphical interface? What are the psychological principles underlying voice user interfaces? What do I need to know about error handling in voice applications and accommodating both novice and experienced users?

How can I make use of newer technologies like speaker authentication?

What about development tools? How can I evaluate and select the right tools?

What can I expect when deploying a spoken dialog system? How is deploying a spoken dialog system different from deploying a web application? What details do I have to be aware of for the deployment to succeed?

What can we expect these systems to do in the future? What kinds of new capabilities are about to emerge from research laboratories?

For professional speech researchers, there is a rich technical literature covering many years of primary research in speech. However, this literature is not necessarily applicable to the needs of business people, application developers, and students who are interested in learning about the practical uses of speech technology. On the other hand, while existing introductory resources cover the basic mechanics of development ofapplication development as well as aspects of the voice user interface, they dona (TM)t go far enough in dealing with the details that have to be taken into account to make spoken dialog systems successful in practice. Whata (TM)s missing is information in between the in-depth technical literature and the more introductory development resources. The goal of this book is to provide information for anyone who wants to take the next step beyond the basics of current speech applications but isna (TM)t yet ready to dive into the technical literature. It is hoped that this book will help project managers, application developers, and students gain a fuller and more complete understanding of spoken dialog technology and the practical aspects of developing and deploying spoken dialog applications.

This book contains a selection of refereed papers presented at the 1st Wo- shop on Machine Learning for Multimodal Interaction (MLMI 2004), held at the "Centre du Parc," Martigny, Switzerland, during June 21-23, 2004. The workshop was organized and sponsored jointly by three European projects, - AMI, Augmented Multiparty Interaction, http: //www.amiproject.org - PASCAL, Pattern Analysis, Statistical Modeling and Computational Learning, http: //www.pascal-network.org - M4, Multi-modal Meeting Manager, http: //www.m4project.org as well as the Swiss National Centre of Competence in Research (NCCR): - IM2: Interactive Multimodal Information Management, http: //www.im2.ch MLMI 2004 was thus sponsored by the European Commission and the Swiss National Science Foundation. Given the multiple links between the above projects and several related - search areas, it was decided to organize a joint workshop bringing together - searchers from the di?erent communities working around the common theme of advanced machine learning algorithms for processing and structuring mul- modal human interaction in meetings. The motivation for creating such a forum, which could be perceived as a number of papers from di?erent research dis- plines, evolved from a real need that arose from these projects and the strong motivation of their partners for such a multidisciplinary workshop. This asse- ment was indeed con?rmed by the success of this ?rst MLMI workshop, which attracted more than 200 participants.

IJCNLP 2004 heralded a new era for computational linguistics and natural l- guage processing in Asia, as it coincided with the launching of the Asian F- eration of NLP Associations (AFNLP) in Sanya, Hainan, China. This was a timely development for the most populous and linguistically diversi?ed region in the world, and there is little wonder that this conference managed to draw over 200 participants. Following an enthusiastic response to the call for papers from 19regionsand the vigorousand rigorouse?ortsof the ProgramCommittee Co-chairs, the sizable collection of papers presented at this conference enabled AFNLP to be compared with related organizations such as COLING and ACL, which have been in existence for more than 40 years. Theorganizersrecognizedthatitisimportantforseriousattemptstobemade to increaseandimprovee?ortsinthis areaallacrossAsia.Towardsthisend, and to contribute to a better awarenessof topical issues, IJCNLP 2004 included two panels of special interest: (1) Panel on Emerging Asian Language Processing E?orts, and (2) Panel on Multilingual NLP for Public Information Services, which was devoted to the NLP requirements envisioned by the organizers of the 2008 Olympics. There were also two thematic sessions on (a) Natural Language TechnologyinMobileInformationRetrievalandTextProcessingUserInterfaces, and(b)TextMininginBiomedicine.Theo?eringsofthisconferencewerefurther enriched by tutorials and workshops as well as an Asian Symposium on Natural Language Processing to Overcome Language Barriers, organized as a satellite eventbytheInstitute ofElectronics, InformationandCommunicationEngineers (IEICE) and the Communications Research Laboratory (CRL) of Japa

Parsing can be defined as the decomposition of complex structures into their constituent parts, and parsing technology as the methods, the tools, and the software to parse automatically. Parsing is a central area of research in the automatic processing of human language. Parsers are being used in many application areas, for example question answering, extraction of information from text, speech recognition and understanding, and machine translation. New developments in parsing technology are thus widely applicable.

This book contains contributions from many of today's leading researchers in the area of natural language parsing technology. The contributors describe their most recent work and a diverse range of techniques and results. This collection provides an excellent picture of the current state of affairs in this area. This volume is the third in a series of such collections, and its breadth of coverage should make it suitable both as an overview of the current state of the field for graduate students, and as a reference for established researchers.

CICLing 2005 (www.CICLing.org) was the 6th Annual Conference on Intelligent Text Processing and Computational Linguistics. It was intended to provide a balanced view of the cutting-edge developments in both the theoretical foundations of computational linguistics and the practice of natural-language text processing with its numerous applications. A feature of CICLing conferences is their wide scope that covers nearly all areas of computational linguistics and all aspects of natural language processing applications. This year we were honored by the presence of our keynote speakers Christian Boitet (CLIPS-IMAG, Grenoble), Kevin Knight (ISI), Daniel Marcu (ISI), and Ellen Riloff (University of Utah), who delivered excellent extended lectures and organized vivid discussions and encouraging tutorials; their invited papers are published in this volume. Of 151 submissions received, 88 were selected for presentation; 53 as full papers and 35 as short papers, by exactly 200 authors from 26 countries: USA (15 papers); Mexico (12); China (9.5); Spain (7.5); South Korea (5.5); Singapore (5); Germany (4.8); Japan (4); UK (3.5); France (3.3); India (3); Italy (3); Czech Republic (2.5); Romania (2.3); Brazil, Canada, Greece, Ireland, Israel, the Netherlands, Norway, Portugal, Sweden, Switzerland (1 each); Hong Kong (0.5); and Russia (0.5) including the invited papers. Internationally co-authored papers are counted in equal fractions.

Interested in how an efficient search engine works? Want to know what algorithms are used to rank resulting documents in response to user requests? The authors answer these and other key information retrieval design and implementation questions.

This book is not yet another high level text. Instead, algorithms are thoroughly described, making this book ideally suited for both computer science students and practitioners who work on search-related applications. As stated in the foreword, this book provides a current, broad, and detailed overview of the field and is the only one that does so. Examples are used throughout to illustrate the algorithms.

The authors explain how a query is ranked against a document collection using either a single or a combination of retrieval strategies, and how an assortment of utilities are integrated into the query processing scheme to improve these rankings. Methods for building and compressing text indexes, querying and retrieving documents in multiple languages, and using parallel or distributed processing to expedite the search are likewise described.

This edition is a major expansion of the one published in 1998. Besides updating the entire book with current techniques, it includes new sections on language models, cross-language information retrieval, peer-to-peer processing, XML search, mediators, and duplicate document detection.

Welcome to NLDB04, the Ninth International Conference on the Application of Natural Language to Information Systems, held at the University of Salford, UK d- ing June 23-25, 2004. NLDB04 follows on the success of previous conferences held since 1995. Early conferences then known as Application of Natural Language to Databases, hence the acronym NLDB, were used as a forum to discuss and disse- nate research on the integration of natural language and databases and were mainly concerned with natural language based queries, database modelling and user int- faces that facilitate access to information. The conference has since moved to enc- pass all aspects of Information Systems and Software Engineering. Indeed, the use of natural language in systems modelling has greatly improved the development process and benefited both developers and users at all stages of the software development process. The latest developments in the field of natural language and the emergence of new technologies has seen a shift towards storage of large semantic electronic dictionaries, their exploitation and the advent of what is now known as the semantic web. Inf- mation extraction and retrieval, document and content management, ontology dev- opment and management and natural language conversational systems are becoming regular tracks in the last NLDB conferences. NLDB04 has seen a 50% increase in the number of submissions and has est- lished itself as one of the leading conferences in the area of applying natural language to information systems in its broader sense.

This volume contains the papers that were accepted for presentation at the - ternationalConferenceonT X, XML, andDigitalTypography, jointlyheld with E the 25th Annual Meeting of the T X Users Group in Xanthi, Greece in the sum- E mer of2004.Theterm DigitalTypography refersto thepreparationofprinted matter using only electronic computers and electronic printing devices, such as laser-jetprinters.Thedocumentpreparationprocessinvolvesmainlytheuseofa digital typesetting system as well as data representation technologies. TXand E its o?spring are beyond doubt the most successful current digital typesetters, while XML is the standard for text-based data representation for both business and scienti?c activities. Allpapersappearinginthisvolumewerefullyrefereedbythemembersofthe program committee. The papers were carefully selected to re?ect the research work that is being done in the ?eld of digital typography using T X and/or its E o?spring. The problems for which comprehensivesolutions have been proposed include proper multilingual document preparation and XML document processing and generation. The proposed solutions deal not simply with typesetting issues, but also related issues in document preparation, such as the manipulation of c- plex bibliographic databases, and automatic conversion of text expressed in one grammaticalsystem to a more recent one (as for the Greek language, converting between monotonic Greek and polytonic Greek). The conference is being graciously hosted by the Democritus University of Thrace in Xanthi and by the Greek T X Friends. We wish to thank Basil K."

The Third International Conference on Natural Language Generation (INLG 2004) was held from 14th to 16th July 2004 at Careys Manor, Brockenhurst, UK. Supported by the Association for Computational Linguistics Special - terest Group on Generation, the conference continued a twenty-year tradition of biennial international meetings on research into natural language generation. Recent conference venues have included Mitzpe Ramon, Israel (INLG 2000) and New York, USA (INLG 2002). It was our pleasure to invite the thriving and friendly NLG research community to the beautiful New Forest in the south of England for INLG 2004. INLG is the leading international conference in the ?eld of natural language generation. It provides a forum for the presentation and discussion of original research on all aspects of the generation of language, including psychological modelling of human language production as well as computational approaches to the automatic generation of language. This volume includes a paper by the keynote speaker, Ardi Roelofs of the Max Planck Institute for Psycholingu- tics and the F. C. Donders Centre for CognitiveNeuroimaging,18 regular papers reportingthelatestresearchresultsanddirections, and4studentpapersdescr- ing doctoral work in progress. These papers reveal a particular concentration of current research e?ort on statistical and machine learning methods, on referring expressions, and on variation in surface realisation. The papers were selected from 46 submissions from all over the world (27 from Europe, 13 from North America, 6 from elsewhere), which were subjected to a rigorous double-blind reviewing process undertaken by our hard-working programme committee

The International Conference on Asian Digital Libraries (ICADL) is an annual international forum that provides opportunities for librarians, researchers and experts to exchange their research results, innovative ideas, service experiences and state-- the-art developments in the field of digital libraries. Building on the success of the first six ICADL conferences, the 7th ICADL conference hosted by the Shanghai Jiao Tong University and the Shanghai Library in Shanghai, China aimed to further strengthen the academic collaboration and strategic alliance in the Asia- Pacific Region in the development of digital libraries. The theme of ICADL 2004 was: Digital library: International Collaboration and Cross-fertilization, with its focus on technology, services, management and localization. The conference began with an opening ceremony and the conference program featured 9 keynote speeches and 5 invited speeches by local and international experts. During the 3-day program, 40 research paper presentations were given in 3 parallel sessions. The conference also included 6 tutorials and an exhibition. The conference received 359 submissions, comprising 248 full papers and 111 short papers. Each paper was carefully reviewed by the Program Committee members. Finally, 44 full papers, 15 short papers and 37 poster papers were selected. On behalf of the Organizing and Program Committees of ICADL 2004, we would like to express our appreciation to all authors and attendees for participating in the conference. We also thank the sponsors, Program Committee members, supporting organizations and helpers for making the conference a success. Without their efforts, the conference would not have been possible.

Human conversational partners are able, at least to a certain extent, to detect the speaker s or listener s emotional state and may attempt to respond to it accordingly. When instead one of the interlocutors is a computer a number of questions arise, such as the following: To what extent are dialogue systems able to simulate such behaviors? Can we learn the mechanisms of emotional be- viors from observing and analyzing the behavior of human speakers? How can emotionsbeautomaticallyrecognizedfromauser smimics, gesturesandspeech? What possibilities does a dialogue system have to express emotions itself? And, very importantly, would emotional system behavior be desirable at all? Given the state of ongoing research into incorporating emotions in dialogue systems we found it timely to organize a Tutorial and Research Workshop on A?ectiveDialogueSystems(ADS2004)atKlosterIrseein GermanyduringJune 14 16, 2004. After two successful ISCA Tutorial and Research Workshops on Multimodal Dialogue Systems at the same location in 1999 and 2002, we felt that a workshop focusing on the role of a?ect in dialogue would be a valuable continuation of the workshop series. Due to its interdisciplinary nature, the workshop attracted submissions from researchers with very di?erent backgrounds and from many di?erent research areas, working on, for example, dialogue processing, speech recognition, speech synthesis, embodied conversational agents, computer graphics, animation, user modelling, tutoring systems, cognitive systems, and human-computer inter- tion."

Spoken Dialogue Technology provides extensive coverage of spoken dialogue systems, ranging from the theoretical underpinnings of the study of dialogue through to a detailed look at a number of well-established methods and tools for developing spoken dialogue systems. The book enables students and practitioners to design and test dialogue systems using several available development environments and languages, including the CSLU toolkit, VoiceXML, SALT, and XHTML+ voice. This practical orientation is usually available otherwise only in reference manuals supplied with software development kits. The latest research in spoken dialogue systems is presented along with extensive coverage of the most relevant theoretical issues and a critical evaluation of current research prototypes. A dedicated web site containing supplementary materials, code, links to resources will enable readers to develop and test their own systems (). Previously such materials have been difficult to track down, available only on a range of disparate web sites and this web site provides a unique and useful reference source which will prove invaluable.

Mathematical theorem proving has undergone an impressive development during the last two decades, resulting in a variety of powerful systems for applications in mathematical deduction and knowledge processing. Natural language processing has become a topic of outstanding relevance in information technology, mainly due to the explosive growth of the Web, where by far the largest part of information is encoded in natural language documents.

This monograph focuses on the development of inference tools tailored to applications in natural language processing by demonstrating how the model generation paradigm can be used as a framework for the support of specific tasks in natural language interpretation and natural language based inference in a natural way.

The book appears at a pivotal moment, when much attention is being paid to the task of adding a semantic layer to the Web, and representation and processing of natural language based semantic information pops up as a primary requirement for further technological progress.

This volume contains the Proceedings of the 7th International Conference on Text, Speech and Dialogue, held in Brno, Czech Republic, in September 2004, under the auspices of the Masaryk University. This series of international conferences on text, speech and dialogue has come to c- stitute a major forum for presentation and discussion, not only of the latest developments in academic research in these ?elds, but also of practical and industrial applications. Uniquely, these conferences bring together researchers from a very wide area, both intellectually and geographically, including scientists working in speech technology, dialogue systems, text processing, lexicography, and other related ?elds. In recent years the conference has dev- oped into aprimary meetingplacefor speech and languagetechnologistsfrom manydifferent parts of the world and in particular it has enabled important and fruitful exchanges of ideas between Western and Eastern Europe. TSD 2004 offered a rich program of invited talks, tutorials, technical papers and poster sessions, aswellasworkshops andsystemdemonstrations. Atotalof78paperswereaccepted out of 127 submitted, contributed altogether by 190 authors from 26 countries. Our thanks as usual go to the Program Committee members and to the external reviewers for their conscientious and diligent assessment of submissions, and to the authors themselves for their high-quality contributions. We would also like to take this opportunity to express our appreciation to all the members of the Organizing Committee for their tireless efforts in organizing the conference and ensuring its smooth running.

This book constitutes the refereed proceedings of the 10th International Conference on Computer Analysis of Images and Patterns, CAIP 2003, held in Groningen, The Netherlands in August 2003. The 94 revised papers presented were carefully reviewed and selected from 160 submissions. The papers are organized in topical sections on analysis and understanding, video analysis, segmentation, shape, classification, face recognition, interpolation and spatial transformations, and filtering.

For over two decades, this comprehensive manual has been the standard introduction and complete reference for writing articles and books containing mathematical formulas. If the reader requires a streamlined approach to learning LaTeX for composing everyday documents, Gratzer's (c) 2014 Practical LaTeX may also be a good choice. In this carefully revised fifth edition, the Short Course has been brought up to date and reflects a modern and practical approach to LaTeX usage. New chapters have been added on illustrations and how to use LaTeX on an iPad. Key features: An example-based, visual approach and a gentle introduction with the Short Course A detailed exposition of multiline math formulas with a Visual Guide A unified approach to TeX, LaTeX, and the AMS enhancements A quick introduction to creating presentations with formulas From earlier reviews: Gratzer's book is a solution. -European Mathematical Society Newsletter There are several LaTeX guides, but this one wins hands down for the elegance of its approach and breadth of coverage. -Amazon.com, Best of 2000, Editor's choice A novice reader will be able to learn the most essential features of LaTeX sufficient to begin typesetting papers within a few hours of time... An experienced TeX user, on the other hand, will find a systematic and detailed discussion of LaTeX fea tures. -Report on Mathematical Physics A very helpful and useful tool for all scientists and engineers. -Review of Astronomical Tools

Recent Advances in Example-Based Machine Translation is of relevance to researchers and program developers in the field of Machine Translation and especially Example-Based Machine Translation, bilingual text processing and cross-linguistic information retrieval. It is also of interest to translation technologists and localisation professionals.

Recent Advances in Example-Based Machine Translation fills a void, because it is the first book to tackle the issue of EBMT in depth. It gives a state-of-the-art overview of EBMT techniques and provides a coherent structure in which all aspects of EBMT are embedded. Its contributions are written by long-standing researchers in the field of MT in general, and EBMT in particular. This book can be used in graduate-level courses in machine translation and statistical NLP.

The International Conference TSD 2003, the sixth event in the series on Text, Speech, and Dialogue, which originated in 1998, presents state-of-the-art technology and - cent achievements in the ?eld of natural language processing. This year's conference includes invited talks given by top-class researchers (Frederick Jelinek from Johns H- kinsUniversityofBaltimore, SadaokiFuruifromtheUniversityofTechnologyinTokyo, President of ISCA, and Steven Krauwer from the Institute of Linguistics of Utrecht U- versity), plenary and problem-oriented sessions, as well as poster sessions and dem- strations involving 28 functional applications. The conference declares its intent to be an interdisciplinary forum, which intertwines researchinspeechandlanguageprocessingaswellasresearchintheEasternandWestern hemispheres. We feel that the mixture of different approaches and applications gives agreatopportunitytogetacquaintedwiththecurrentactivitiesinallaspectsoflanguage communication and to witness the amazing vitality of research from the former East Block countries. The ?nancial support of ISCA (International Speech Communication Association) enables the wide attendance of researchers from all active regions of the world. This volume contains a collection of all the papers presented at the international conf- ence organized by the Faculty of Applied Sciences of the University of West Bohemia in Pilsen in collaboration with the Faculty of Informatics, Masaryk University in Brno, ? and held in the beautiful city of Ceske Budejo ? vice (South Bohemia, Czech Republic), September 8-12, 2003. Each of the submitted papers was thoroughly reviewed by three membersoftheconferencereviewingteamconsistingofmorethan40world-famouss- cialists in the conference topic areas."