Workshop on Finite-State Methods in Natural Language Processing

an EACL 2003 Workshop

13 – 14 April 2003

Agro Hotel, Budapest, Hungary

This workshop is a follow-up to FSMNLP’98 (Ankara) and FSMNLP’01 (Helsinki) workshops, and will be a forum for researchers working on theoretical aspects and applications of finite state methods in natural language processing. This year’s workshop will have special themes on and sessions for "Linguistic Resources" and "Finite State Applications for Lesser-studied Languages", so submissions from researchers in these areas are especially welcome. In addition to these themes, papers are invited on all aspects of finite state techniques and their applications in natural language processing including but not limited to:


April 13. Morning: tutorial, afternoon: paper presentations.

April 14. Paper presentations.

During the first day, the tutorial and papers will be presented mainly for an audience of (computational) linguists interested in lesser-studied/minority languages, e.g. from the Bantu, American Indian, Turkic, Sámi, Semitic, Austronesian etc. families.

The second day will be mainly dedicated to finite-state methods combined with precise linguistic descriptions, e.g. lexical resources, linguistic grammars, ambiguity-adapted text representations etc.

Audience: Graduate students and practicing linguists or computational linguists working on or interested in finite-state technlogy and its uses in developing tools for morphological processing, tagging, parsing, lexicology etc. About 50 participants are expected.

Organizers: Ken Beesley (XRCE, France), Lauri Karttunen (Parc Inc., USA), Éric Laporte (Université de Marne-la-Vallée, France), Denis Maurel (Université de Tours, France), Kemal Oflazer (Sabanci University, Turkey), Elisabete Ranchhod (Universidade de Lisboa & Instituto Superior Técnico, Portugal), Emmanuel Roche (Teragram, USA).

Programme Committee: Iñaki Alegria (University of Basque Country), Ken Beesley (XRCE), Steven Bird (University of Melbourne), Cédrick Fairon (Université catholique de Louvain-la-Neuve), Franz Guenthner (Universität München), Arvi Hurskainen (University of Helsinki), Lauri Karttunen (Parc Inc.), George Kiraz (AT & T Research), Éric Laporte (Université de Marne-la-Vallée), Denis Maurel (Université de Tours, France), Mike Maxwell (Linguistic Data Consortium), Kemal Oflazer (Sabanci University), Elisabete Ranchhod (Universidade de Lisboa & Instituto Superior Técnico, Portugal), Emmanuel Roche (Teragram, USA), Jean Senellart (Systran).

Important Dates:

Deadline for Submission of Papers: *** Attention, extended deadline *** Monday January 13, 2003

Notification of Acceptance: 28 January 2003

Camera-ready copies due: 13 February 2003

Workshop: 13-14 April 2003

Submission Format:

Submissions must be electronic only, and should consist of full papers of max. 8 pages (inclusive of references, tables, figures and equations). Authors are strongly encouraged to use the following stylefiles, available on paper format guidelines:



acl.bst (BibTeX bibliography style file)

Sample LaTeX paper, Sample bibliography, Sample makefile for latex-based build (NO WARRANTY though :)),

These formats will ease the transition to the final format, which is essentially equivalent. Please note that if accepted, the final camera-ready version of the paper must be formatted for A4-sized paper. An electronic version of the paper, formatted for A4 or a letter-size paper must be received by January 7, 23:00 GMT at the following address: Please use gzip or plain old zip (or PKZIP) for compression to ensure nothing is lost during the email transfer.


Participants pay a registration fee. They are not required to register for the main conference as well, but if they do not they will pay a higher registration fee. More information will be published on the main conference page (

Contact info:

Matthieu Constant

Tel.: 33 - 1 60 95 77 38

IGM, University of Marne-la-Vallée

5, bd Descartes

77454 Marne-la-Vallée CEDEX 2