A Workshop on Acquisition and Management
of Multilingual Lexicons

In conjunction with RANLP-2007
(The International Conference on Recent Advances in Natural Language Processing)

Sponsored by Expert System Inc.

Endorsed by the ACL Special Interest Group on the Lexicon (ACL-SIGLEX)

Borovetz, Bulgaria
September 30, 2007

The current trend of information exchange on the Internet to become ever more multilingual has stimulated new important developments in the field of multilingual Natural Language Processing (NLP). The present workshop is concerned with the problem of automatic management of lexical resources, which lie at the heart of many multilingual technologies.

In recent years one could witness an increased interest of NLP research in the automated discovery of equivalent expressions in different languages. New interesting directions have sprung up, such as the use of the Web and comparable corpora for this task, and new kinds of lexical phenomena, such as multiword expressions and named entities, have come into focus.

This workshop will bring together researchers working on a broad range of problems related to the management of multilingual lexical resources - their acquisition, maintenance, customization, and re-use. The scope of the workshop includes evaluation of multilingual lexicons intended for a broad range of applications: from personalized glossaries for a translation project to large-scale machine-readable dictionaries and databases.

Specific topics of interest for the proposed workshop are:

• Acquisition of lexical knowledge from parallel and comparable corpora, and from the Web
• Porting, merging and domain customisation of existing lexical resources using NLP technologies
• Acquisition of multilingual domain terminology
• Acquisition of translations for multi-word expressions
• Acquisition of translations for polysemous words
• Acquisition of multilingual lexical taxonomies
• Named Entity transliteration
• Acquisition of cognates and loanwords
• Extraction of equivalent free word combinations from comparable corpora
• Applications of multilingual lexicons and their evaluation within:
• Statistical Machine Translation
• Computer-Aided Translation
• Information Retrieval (Question Answering, Text Retrieval, Text Classification and Clustering)
• Knowledge Management

Format. Authors are invited to submit full papers on original, unpublished work in the topic area of this workshop. Papers should be submitted as a PDF file, formatted according to the RANLP 2007 stylefiles and not exceeding 8 pages. The RANLP 2007 stylefiles are available at:

http://lml.bas.bg/ranlp2007/submissions.htm

As reviewing will be blind, the papers should not include the authors' names and affiliations. Furthermore, self-references that reveal the authors' identities should be avoided. Papers that do not conform to these requirements will be rejected without review.

Submission procedure. Please submit your paper at: http://quad.softconf.com/ranlp/amml07/submit.html.

Reviewing. Each submission will be reviewed at least by two members of the Program Committee. Reviewers will be asked to provide detailed comments, and to score submitted papers on the following factors:

• Relevance to the workshop
• Significance and originality
• Technical/methodological accuracy
• References to related work
• Presentation (clarity, organisation, English)

Accepted papers policy. Accepted papers will be published in the workshop proceedings. By submitting a paper at the workshop the authors agree that, in case the paper is accepted for publication, at least one of the authors will attend the workshop; all workshop participants are expected to pay the RANLP-2007 workshop registration fee.

Viktor Pekar
University of Wolverhampton, UK

Diana Inkpen
University of Ottawa, Canada

Andrea Mulloni
Expert System Inc., Italy