Salience refers to the prominence of information; salient items pop out and capture attention. This volume addresses the role of salience in discourse. It illustrates the range of multidisciplinary approaches - their diversities and similarities. The collection of papers covers a variety of research with different foci ranging from discourse entities, to discourse segments, to extra-linguistic factors.

It is a major challenge for linguists to explore the relations between referential choice and the discourse structure in dialogues, because, unlike written modes of discourse, dialogue as an interactional mode of discourse needs careful treatment for linguistic analysis. This book investigates how discourse entities are linked with topic chaining and discourse coherence by showing that the choice and the distribution of referring expressions is correlated with center transition patterns in the centering framework. It provides original empirical research into the use of referring expressions in English and Japanese task-based dialogues, and applies and extends theoretical frameworks which attempt to account for local and global discourse coherence. Using a discourse-based integrated approach to anaphora resolution, Yoshida proposes a unified account on the patterns of use of referring expressions. The book will be of interest to discourse analysts, computational linguists, scholars of semantics and pragmatics, and cross-linguistics researchers.

The ability to produce and understand referring expressions is basic to human language use and human cognition. Reference comprises the ability to think of and represent objects (both real and imagined/fictional), to indicate to others which of these objects we are talking about, and to determine what others are talking about when they use a nominal expression. The articles in this volume are concerned with some of the central themes and challenges in research on reference within the cognitive sciences - philosophy (including philosophy of language and mind, logic, and formal semantics), theoretical and computational linguistics, and cognitive psychology. The papers address four basic questions: What is reference? What is the appropriate analysis of different referring forms, such as definite descriptions? How is reference resolved? and How do speaker/writers select appropriate referring forms, such as pronouns vs. full noun phrases, demonstrative vs. personal pronouns, and overt vs. null/zero pronominal forms? Some of the papers assume and build on existing theories, such as Centering Theory and the Givenness Hierarchy framework; others propose their own models of reference understanding or production. The essays examine reference from a number of disciplinary and interdisciplinary perspectives, informed by different research traditions and employing different methodologies. While the contributors to the volume were primarily trained in one of the four represented disciplines-computer science, linguistics, philosophy and psychology, and use methodologies typical of that discipline, each of them bridges more than one discipline in their methodology and/or their approach.

This volume contains the papers prepared for the 2nd International Conference on Natural Language Processing, held 2-4 June in Patras, Greece. The conference program features invited talks and submitted papers, c- ering a wide range of NLP areas: text segmentation, morphological analysis, lexical knowledge acquisition and representation, grammar formalism and s- tacticparsing,discourse analysis,languagegeneration,man-machineinteraction, machine translation, word sense disambiguation, and information extraction. The program committee received 71 abstracts, of which unfortunately no more than 50% could be accepted. Every paper was reviewed by at least two reviewers. The fairness of the reviewing process is demonstrated by the broad spread of institutions and countries represented in the accepted papers. So many have contributed to the success of the conference. The primary credit, ofcourse, goes to theauthors andto the invitedspeakers. By theirpapers and their inspired talks they established the quality of the conference. Secondly, thanks should go to the referees and to the program committee members who did a thorough and conscientious job. It was not easy to select the papers to be presented. Last, but not least, my special thanks to the organizing committee for making this conference happen.

This edited collection of previously unpublished papers focuses on Centering Theory, an account of local discourse structure. Developed in the context of computational linguistics and cognitive science, Centering theory has attracted the attention of an international interdisciplinary audience. As the authors focus on naturally occurring data, they join the general trend towards empiricism in research on computational models of discourse, providing a significant contribution to a fast-moving field.

This book constitutes the refereed proceedings of the 10th International Conference on Text, Speech and Dialogue, TSD 2007, held in Pilsen, Czech Republic, September 3-7, 2007. The 80 revised full papers presented together with 4 invited papers were carefully reviewed and selected from 198 submissions. The papers present a wealth of state-of-the-art research results in the field of natural language processing with an emphasis on text, speech, and spoken dialogue ranging from theoretical and methodological issues to applications in various fields and with special focus on corpora, texts and tra.