linguistlist.org>
Editor for this issue: Jody Huellmantel <jodylinguistlist.org>
nis.sdu.dk>LREC 2000 workshop: FROM SPOKEN DIALOGUE TO FULL NATURAL INTERACTIVE DIALOGUE. THEORY, EMPIRICAL ANALYSIS AND EVALUATION. 29 May 2000 - immediately before LREC 2000, Athens, Greece http://www.nis.sdu.dk/lrec2000workshop CALL FOR PAPERS - EXTENDED DEADLINE Spoken dialogue systems have been in the marketplace since around 1990. Whereas the first systems only had single word recognition there has been a steady development towards increasingly natural spoken dialogue. The most advanced current systems still work within a limited task domain but some are capable of understanding and replying to fairly long user utterances, coping with various kinds of initiative, and taking a variety of contextual issues into account. Naturalness, as perceived by the user, is closely connected to properties such as allowed user utterance length, grammar, vocabulary, style and initiative. Depending on task and situation, perceived naturalness is also connected to how the user can interact with the system. In human-human communication we normally do not restrict ourselves to using speech-only but also include gesture, facial expression, and bodily posture and we often draw on other information sources such as diagrams, maps and drawings. Natural interactive dialogue and conversational systems are moving centre-stage because of increasing interest in adding other modalities to achieve a larger potential than speech alone can offer. Several recent conversational prototype systems include one or several natural interaction modalities in addition to speech. However, there are many open questions and unsolved or insufficiently explored problems related to extending spoken dialogue management and dialogue interfaces to enable increased natural interactivity. The workshop aims to bring together researchers and developers in the area of natural interactive dialogue. The goal of the workshop is to highlight and evaluate empirically based theories and methods for natural multimodal conversational dialogue management and dialogue interfaces, and their evaluation. Focus will be on key issues such as dialogue initiative, reference, communicative acts, feedback, and cooperativity. TOPICS Topics of interest should fall within theory, empirical analysis, and evaluation of key issues in the transition from spoken dialogue to full natural interactive dialogue. Topics include but are not limited to: - Cooperative natural interactive dialogue interfaces and usability - Experience from natural interactive systems development and evaluation - Integration of natural interactivity modalities - Empirically based theories in support of natural interactive dialogue management and interfaces - Communicative acts (beyond speech acts) - Reference in a multimodal context - Dialogue initiative - Task management - Feedback - Methods for evaluation of natural interactive dialogue management and dialogue interfaces SUBMISSION DETAILS Extended abstracts should be around 4 pages in length. Final papers should not exceed six pages. Extended abstracts must be submitted electronically to lailaMail to author|Respond to list|Read more issues|LINGUIST home page|Top of issue
cs.vassar.edu>***************************************************************** SECOND CALL FOR PAPERS LREC WORKSHOP DATA ARCHITECTURES AND SOFTWARE SUPPORT FOR LARGE CORPORA May 30, 2000 ATHENS, GREECE http://www.cs.vassar.edu/~ide/anc/lrec.html ****************************************************************** SUBMISSION DEADLINE : MARCH 7, 2000 Several software systems for linguistic annotation, search, and retrieval of large corpora have been developed within the natural language processing community over the past several years, including LT-XML (Edinburgh), GATE (Sheffield), IMS Corpus Workbench (Stuttgart), Alembic Workbench (Mitre), MATE (Edinburgh/Odense/Stuttgart), Silfide (Loria/CNRS), SARA (BNC), and several others. Related to and in support of this development, there have also been efforts to develop standards for encoding and various kinds of linguistic annotation, as well as data architectures (e.g., TIPSTER, TalkBank) etc. Still other developments, such as the introduction of XML and the powerful XSL transformation language and work on semi-structured data (e.g., the work of the Lore group at Stanford), have also impacted the ways in which corpora and other linguistic resources can be represented, stored, and accessed. Approaches to the fundamental design of the formats, data, and tools are varied among current systems for the annotation and exploitation of linguistic corpora. A primary reason for this diversity is that most developers are concerned with only one aspect of the creation/annotation/exploitation process. However, in order to work effectively toward commonality, the phases of the process must be considered as a whole. This demands bringing together researchers and developers from a variety of domains in text, speech, video, etc., many of whom have previously had little or no contact. This workshop is intended to bring these groups together to look broadly at the technical issues that bear on the development of software systems for the annotation and exploitation of linguistic resources. The goal is to lay the groundwork for the definition of a data and system architecture to support corpus annotation and exploitation that can be widely adopted within the community. Among the issues to be addressed are: o layered data architectures o system architectures for distributed databases o support for plurality of annotation schemes o impact and use of XML/XSL o support for multimedia, including speech and video o tools for creation, annotation, query and access of corpora o mechanisms for linkage of annotation and primary data o applicability of semi-structured data models, search and query systems, etc. o evaluation/validation of systems and annotations - -------------------------------------------------------------------------- Submissions Papers should be submitted in electronic form (preferably postscript, but plain ascii, MS Word RTF, or HTML are acceptable) to ideMail to author|Respond to list|Read more issues|LINGUIST home page|Top of issue