Date: 14 Jun 1995 ----------------- ====================================================================== TOPICS: 1. EWNLG paper available online - Ma(r)king concessions in English and German (stede@faw.uni-ulm.de Manfred Stede) 2. Announcing the NLP/CL universe (Dragomir R. Radev ) 3. New documentation of Generalized Upper Model (John Bateman ) 4. Job offer: NLG in Health Education (alison Cawsey ) 5. New Corpus from the LDC Air Travel Information System (LDC Office ) 6. CFP: Workshop on Spoken Language Generation and Multimodal Information Systems 2-3/Nov 95 Darmstadt (John Bateman" ) 7. Project Information: The SPEAK! Project - Speech Generation in Multimodal Information Systems (John Bateman) 8. Job offer: CMU / NL-Soar (Jill Fain ) ====================================================================== Topic 1: From: stede@faw.uni-ulm.de (Manfred Stede) Subject: EWNLG paper available online the following paper from the 95 European NLGWS is available on the cmp-lg archive, http://xxx.lanl.gov/cmp-lg Title: Ma(r)king concessions in English and German Author: Brigitte Grote (FAW Ulm), Nils Lenke (Universitaet Duisburg), Manfred Stede (FAW Ulm and University of Toronto) Comments: 23 pages, uuencoded compressed postscript Abstract: In order to generate cohesive discourse, many of the relations holding between text segments need to be signalled to the reader by means of cue words, or {\em discourse markers}. Programs usually do this in a simplistic way, e.g., by using one marker per relation. In reality, however, language offers a very wide range of markers from which informed choices should be made. In order to account for the variety and to identify the parameters governing the choices, detailled linguistic analyses are necessary. We worked with one area of discourse relations, the Concession family, identified its underlying pragmatics and semantics, and undertook extensive corpus studies to examine the range of markers used in both English and German. On the basis of an initial classification of these markers, we propose a generation model for producing bilingual text that can incorporate marker choice into its overall decision framework. ====================================================================== Topic 2: From: "Dragomir R. Radev" Subject: Announcing the NLP/CL universe The Association for Computational Linguistics announces the availability of the NLP/CL UNIVERSE, a comprehensive World-Wide Web database of Web-accessible material related to computational linguistics and natural-language processing. The Universe lists conference announcements; academic departments and institutes, companies, organizations, and individual researchers; books, corpora, and bibliographies; subject-specific information; and information in a variety of other categories. The system allows automated submission of information in all categories through the use of HTML forms. Submissions are moderated to maintain quality and uniformity. Through the submission feature, the CL community can keep the NLP/CL Universe up-to-date and complete. The NLP/CL Universe is accessible through the ACL home page ("http://www.cs.columbia.edu/~acl/home.html"), from the cmp-lg home page ("http://xxx.lanl.gov/cmp-lg/"), or directly ("http://www.cs.columbia.edu/~radev/cgi-bin/universe.cgi"). The system is maintained and moderated by Dragomir Radev (radev@cs.columbia.edu). .............................................................................. THE DEMISE OF CMP-LG CONFERENCE LISTINGS The CMP-LG NEWS will no longer provide listings of conferences. The NLP/CL Universe admirably takes over this function. For direct access to current conference listings, use the URL "http://www.cs.columbia.edu/~radev/cgi-bin/universe.cgi?CONFERENCE". Conference organizers should take advantage of the submission feature of the NLP/CL Universe to submit their announcements there. .............................................................................. ON-LINE PROCEEDINGS OF ACL-95 AVAILABLE An on-line proceedings for the 33rd Annual Meeting of the Association for Comptuational Linguistics (ACL '95), to be held in June 1995 at MIT in Cambridge, Massachusetts, has been added to the cmp-lg WWW home page. Well over half of the papers submitted to the conference are available through the on-line proceedings. Authors of ACL '95 papers who have not already done so are urged to submit their papers to cmp-lg and send a note to cl-server@das.harvard.edu notifying us to add a link from the proceedings page. Conference organizers wishing to have on-line proceedings made available through cmp-lg should contact the server at cl-server@das.harvard.edu. .............................................................................. FOR FURTHER INFORMATION For further information about (among other topics) submission of papers to the server, subscribing or canceling your subscription, requesting full text of any of the papers above, retrieving macro files for these papers, searching past listings, or submitting comments to the server operators, send a message: To: CMP-LG@XXX.LANL.GOV Subject: help or, better yet, access the hypertext help information through the WWW/Mosaic interface at "http://xxx.lanl.gov/cmp-lg/". ****************************************************************************** ====================================================================== Topic 3: From: "Dr. John Bateman" Subject: New documentation of Generalized Upper Model There is a new draft version of documentation for the Generalized Upper Model, a multilingual outgrowth of the Penman Upper Model. It is available on WWW at: http://www.darmstadt.gmd.de/publish/komet/gen-um/newUM.html We are soliciting feedback concerning both content and documentation style. Best wishes, John Bateman Renate Henschel Fabio Rinaldi. ====================================================================== Topic 4: From: alison Subject: Job offer: NLG in Health Education University of Glasgow Departments of Computing Science and Public Health Two Research Associate Positions Two 3 year research associate posts are available to work on on an EPSRC funded project looking at the use of text planning and user modelling techniques in the provision of interactive personalised health education materials. One post is available on the UK RA 1A scale (around 16000 pounds pa, according to age and experience), and the other on the RA 1B scale (around 14300 pounds pa). Candidates for the 1A post will normally have a higher degree in a relevant area, and will be expected to work mainly on the development of the techniques for the appropriate selection and presentation of interactive personalised health information. Candidates for the 1B post should have good computing experience and preferably experience of health services. Job share or part-time applications may be considered. The 1B RA will be expected to collaborate with health professionals in the development and evaluation of prototype systems. There may be opportunities to register for a higher degree. The closing date for applications is 1st September. Starting dates are negotiable, but the preferred dates are October 1995 for the 1A position and April 1995 for the 1B position. Some further details of the posts and the project are available from "http://www.dcs.gla.ac.uk/~alison/job.html" or by emailing alison@dcs.glasgow.ac.uk. Letters of application should be sent, together with a copy of a recent CV and names and addresses of two referees, to: Dr Alison Cawsey, Department of Computing Science, University of Glasgow, Glasgow, G12 8QQ. (Note: One position may move to Heriot Watt University, Edinburgh. Other details will remain the same). ====================================================================== Topic 5: From: LDC Office Subject: New Corpus from the LDC Announcing a NEW RELEASE from the LINGUISTIC DATA CONSORTIUM: Air Travel Information System ATIS3 TEST DATA This set of discs contains a corpus of speech and natural language data collected under the auspices of the Advanced Research Projects Agency Spoken Language Systems (ARPA-SLS) technology development program. The corpus, which contains data in the Air Travel Information Services (ATIS) domain, was designed by the ARPA-SLS Multi-site Atis Data COllection Working (MADCOW) group and was collected by five sites at locations across the U.S.: BBN Systems & Technologies, Cambridge, MA Carnegie Mellon University, Pittsburgh, PA MIT Laboratory for Computer Science, Boston, MA National Institute for Standards and Technology, Gaithersburg, MD SRI International, Menlo Park, CA The corpora on this set of discs is part of the third phase of collection of ATIS data (ATIS3) and comprises the development test (NIST Speech Disc 17-4.2) and evaluation test material (NIST Speech Disc 17-5.1) used in the December 1994 ARPA SLS Benchmark Tests. As in the previous ATIS corpora, the speech contained in this corpus was elicited by presenting subjects with various hypothetical travel planning scenarios to solve. The resulting spontaneous spoken queries were recorded as the subjects interacted with partially or completely automated ATIS systems to solve the scenarios. Note that the ATIS3 training data is available on NIST Speech Discs 17-1.1-17-3.1. The recorded speech has been transcribed and annotated with categorizations and canonical reference answers. All of the utterances on these discs have been recorded using a close-talking, noise-cancelling head-mounted Sennheiser microphone. For some subjects, secondary (noisier) microphone data was recorded simultaneously as well. These discs also contain the ATIS3 46 city/52 airport relational database, a revised Principles of Interpretation, and test implementation and scoring instructions as well as other general documentation. The ATIS3 corpus has been verified, collated, documented, and produced on CD-ROM by the National Institute of Standards and Technology (NIST) in cooperation with MADCOW and distributed by the Linguistic Data Consortium (LDC). Further information about the LDC and its available corpora can be accessed on the Linguistic Data Consortium WWW Home Page at URL http://www.cis.upenn.edu/~ldc. Information is also available via ftp at ftp.cis.upenn.edu under pub/ldc; for ftp access, please use "anonymous" as your login name, and give your email address when asked for password. ====================================================================== Topic 6: From: "Dr. John Bateman" Subject: CFP: Workshop on Spoken Language Generation and Multimodal Information Systems 2ND `SPEAK!' WORKSHOP: SPEECH GENERATION IN MULTIMODAL INFORMATION SYSTEMS AND PRACTICAL APPLICATIONS 2nd-3rd November 1995 GMD/IPSI, Darmstadt, Germany ******************* CALL FOR CONTRIBUTIONS ******************* This workshop aims to bring together researchers, developers, and potential producers and marketers of multimodal information systems in order to consider the role of *spoken language synthesis* in such systems. Not only do we need to be able to produce spoken language appropriately---including effective control of intonation---but also we need to know in which practical contexts spoken language is most beneficial. This requires a dialogue between those providing spoken natural language technology and those considering the practical use of multimodal information systems. The workshop will consist of paper presentations and practical demonstrations, as well as a roundtable discussion on the best strategies for pursuing the practical application of spoken language synthesis technology in information systems. Suggested Topic Areas/Themes include, but are not limited to: * functional control of intonation in synthesized speech * use of speech in intelligent interfaces for information systems * integration of speech into automatic query systems * cooperative integration of speech with text generation for information systems * evaluation strategies for information systems involving speech synthesis * applications for information systems with spoken language output capabilities * practical requirements for information systems with spoken language capabilities. Potential participants are invited to submit short statements of interest indicating whether they would be interested in presenting a paper, offering a system demonstration, participating in the round table discussion, or simply attending. Statements of interest and extended abstracts (max. 7 pages) should be sent by 1st. October by e-mail to: `bateman@gmd.de' or by post to: John A. Bateman, GMD/IPSI, Dolivostr. 15, D-64293 Darmstadt, Germany. Extended abstracts will be made available at the workshop. During the workshop current results and demonstrations of the EU Copernicus Program Project `Speak!' will also be given (see attachment). ====================================================================== Topic 7: From: "Dr. John Bateman" Project Information: The SPEAK! Project: Speech Generation in Multimodal Information Systems "SPEAK!" is a European Union funded project (COPERNICUS '93 Project No. 10393) whose aim is to embed spoken natural language synthesis technology with sophisticated user interfaces in order to improve access to information systems. Multimedia technology and knowledge-based text processing enhance the development of new types of information systems which not only offer references or full-text documents to the user but also provide access to images, graphics, audio and video documents. This diversification of the in formation offered has to be supported by easy-to-use multimodal user interfaces, which are capable of presenting each type of information item in a way that it can be perceived and processed effectively by the user. Users can easily process simultaneously the graphical medium of information presentation and the linguistic medium. The separation of mode is also quite appropriate for the different functionalities of the main graphical interaction and the supportive meta-dialogue carried out linguistically. We believe, therefore, that a substantial improvement in both functionality and user acceptance is to be achieved by the integration of spoken languages capabilities. However, text-to-speech devices commercially available today produce speech that sounds unnatural and that is hard to listen to. High quality synthesized speech that sounds acceptable to humans demands appropriate intonation patterns. The effective control of intonation requires synthesizing from meanings, rather than word sequences, and requires understanding of the functions of intonation. In the domain of sophisticated human-machine interfaces, we can make use of the increasing tendency to design such interfaces as independent agents that themselves engage in an interactive dialogue (both graphical and linguistic) with their users. Such agents need to maintain models of their discourses, their users, and their communicative goals. The SPEAK! project, which was launched recently as a cooperation between the Speech Research Technology Laboratory of the TECHNICAL UNIVERSITY OF BUDAPEST and the TECHNICAL UNIVERSITY OF DARMSTADT (in cooperation with GMD-IPSI), aims at developing such an interface for a multimedia retrieval system. At IPSI, the departments KOMET (natural language generation) and MIND (information retrieval dialogues) contribute to this project. The project is to construct a proof-of-concept prototype of a multimodal information system combining graphical and spoken language output in a variety of languages. The work involves four supporting goals: first, to advance the state of the art in the domains of speech synthesis, spoken text generation, and graphical interface design; second, to provide enabling technology for higher functionality information systems that are more appropriate for general public use; third, to significantly improve the public and industrial acceptance of speech synthesis in general and the Hungarian text-to-speech technology elaborated within the project in particular; and, fourth, to act as a focusing point for speech work in Hungary. Contact points: GMD/IPSI, Darmstadt: John Bateman e-mail: bateman@gmd.de fax: +49/6151-869-818 tel: +49/6151-869-826 TU-Budapest: G'eza N'emeth e-mail: NEMETH@ttt-202.ttt.bme.hu fax: +36/1-463-3107 tel: +36/1-463 2401 ====================================================================== Topic 7: From: Jill Fain Subject: job available School of Computer Science, Carnegie Mellon University, Pittsburgh, PA Position: Research Assistant or Post-doctoral fellow, effective May 1, 1995. Contact: Dr. Jill Fain Lehman School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213-3891 by email: jill.lehman@cs.cmu.edu Description: Two-year position working on natural language processing within the Soar project. Our main focus will be to extend the current models of comprehension and generation (NL-Soar) within the context of military simulations. In particular, the current system is oriented toward real-time dialog behavior between intelligent agents (e.g. pilot, wing, air controller) participating in simulated engagements in the tactical air domain. Although this work will continue under the current position, we will also be responsible for providing a real-time, incremental language capability between these agents and command level agents also built within the Soar framework. The natural language project consists of 1 faculty member, 3 graduate students and a post-doc. In addition to the applications mentioned above, current research using NL-Soar includes issues in language acquisition, speech recognition, and simultaneous translation. The language project exists within a larger Soar community (about 15 members at CMU, about 100 active researchers throughout the world). A person filling this position is expected to make significant contributions to the design and implementation of the system, as well as contribute to the intellectual life of the community. Qualifications: Applicants should have a B.S., M.S. or Ph.D. in computer science or computational linguistics. THIS IS A SYSTEM-BUILDING POSTDOC, so a very strong background in building systems is required. Experience in both language generation and comprehension is preferred. Basic knowledge of machine learning techniques helpful. APPLICANT MUST BE ABLE TO START WORK BY SEPTEMBER 1. To apply: send a resume and names of three references to physical or e-mail address above. Please have recommendations letters specifically address the system building strengths and weaknesses of the applicant. CMU is an Equal Opportunity, Affirmative Action Employer. ====================================================================== eof ======================================================================