UCNLG+MT - FINAL CALL FOR PAPERS ================================= ********************************************************************** News: * Submission deadline for full workshop papers extended to 15 June. ********************************************************************** Using Corpora for NLG: Language Generation and MT (UCNLG+MT) is a pre-conference workshop at MT Summit XI, to be held in Copenhagen, 11 September 2007. There are many branches of NLP research where language is generated (MT, summarisation, human-computer dialogue, data-to-text generation, document authoring, etc.). However, for the most part, these form separate research communities and the field called "Natural Language Generation (NLG)" is to some degree isolated from many of them. The UCNLG workshops have the general aims 1. to provide a forum for reporting and discussing data-based methods for generating language in all areas of application; 2. to open up the NLG research field to neighbouring areas in NLP and to foster cross-fertilisation between these research fields; and 3. to promote the sharing of data in NLG and the use of data-based methods of evaluation. The special theme of this second UCNLG workshop is Language Generation and MT. Target language generation is typically given less attention than other aspects of MT, such as evaluation, source language analysis and transfer. Recently there has been increasing interest in combining linguistic knowledge with statistical MT. Conversely, NLG -- where symbolic approaches have long dominated -- has seen increasing interest in probabilistic methods. With this special theme, we would like to explore crossover points and potential for cross-fertilisation between MT and NLG. The workshop also continues from UCNLG'05 in its general focus on data-based methods for language generation and their evaluation. We invite submissions on all aspects of using corpora in the generation of language. Specific topics include, but are not limited to: * Using NLG techniques in MT * Combining statistical MT with rule-based techniques such as those developed in NLG * Introducing linguistic filters into statistical MT * Issues in annotating corpora for language generation * Statistical approaches to deep and/or surface generation * Machine learning methods for deep and/or surface generation * Uses of corpora in the evaluation of automatically generated language * Reuse of corpus resources developed for NLU (e.g. treebanks) in language generation * Domain-specific vs. general-purpose corpora for language generation Invited Speaker: ---------------- Kevin Knight, ISI, University of Southern California, US, will present the keynote address. Discussion Session on Language Generation and MT: ------------------------------------------------- There will be a discussion session on the special theme of the workshop, Language Generation and Machine Translation. It is intended as a discussion forum where people can present short `opinion pieces' on the special theme. Possible topics include, but are by no means limited to, the following: * common research agenda for NLG and MT * given the `more data is better data' mantra of statistical MT, what space is there for linguistically motivated generation? * can a shared task be defined that would interest both NLG and MT researchers? * data resources that can be shared between NLG and MT * methods and tools that can be used for NLG and MT We invite submissions of extended abstracts for this session which should be up to 2 pages long and follow the ACL'07 guidelines using the style files provided at http://ufal.mff.cuni.cz/acl2007/styles/. Abstracts should be sent in PDF format by email to ucnlg@itri.brighton.ac.uk no later than July 1. Submissions will be reviewed by at least two members of the programme committee, to ensure appropriateness of content. If there are more submissions than we can accommodate, then the workshop organisers will make a selection based on the reviews. Extended abstracts will be included in the workshop proceedings. Proceedings: ------------ The proceedings of the workshop will be published by the MT Summit XI conference organisers, in a companion volume to the main conference proceedings. Requirements: ------------- Papers should describe original and unpublished work, emphasizing actual rather than intended work, and should indicate clearly the state of completion of the reported results. Wherever appropriate, concrete evaluation results should be included. Papers that are being submitted to other conferences or workshops should indicate this. Submission information: ----------------------- Submissions should be no longer than 8 (eight) pages, and should follow the ACL'07 guidelines using the style files provided at http://ufal.mff.cuni.cz/acl2007/styles/. Submitted papers should be sent in PDF format by email to ucnlg@itri.brighton.ac.uk no later than 8 June 2007. RTF format is also accepted but not encouraged. Reviewing of papers will be blind. Reviewing will be managed by the international workshop programme committee. Final decisions on the technical programme will be made by the workshop organisers. As reviewing will be blind, the paper should not include the authors' names and affiliations. Self-references that reveal the authors' identity, e.g., "We previously showed (Smith, 1991) ...", should be avoided. Instead, use citations such as "Smith previously showed (Smith, 1991) ...". In the body of the email submitting the paper, please include the authors' names and affiliations, and the paper title. Important Dates: ---------------- 15 June Extended submission deadline for workshop papers 29 June Notification of acceptance to authors of workshop papers 01 July Submission deadline for extended abstracts for Discussion Session on NLG and MT 09 July Notification of acceptance to authors of extended abstracts for Discussion Session on NLG and MT 20 July Camera-ready copy from all authors 11 September UCNLG+MT in Copenhagen Programme Committee: -------------------- Srinivas Bangalore, AT&T, USA Stephan Busemann, DFKI, Germany Robert Dale, Macquarie University, Australia Kevin Knight, ISI, U of Southern California, USA Irene Langkilde-Geary, Brigham Young University, USA Chris Mellish, U of Aberdeen, UK Jon Oberlander, U of Edinburgh, UK Richard Power, Open University, UK Flo Reeder, The Mitre Organisation, USA Ehud Reiter, U of Aberdeen, UK Amanda Stent, SUNY, USA Michael Strube, EML Research, Germany Kees van Deemter, U of Aberdeen, UK Bonnie Webber, U of Edinburgh, UK Mike White, Ohio State University, USA Workshop organisers: -------------------- Anja Belz, NLTG, University of Brighton, UK Sebastian Varges, Information and Communication Technology, University of Trento, Italy Workshop website: ----------------- http://www.nltg.brighton.ac.uk/ucnlg/