CIC Chapter *

CICLing-2005

Sixth International Conference on Intelligent Text Processing and Computational Linguistics

February 13 to 19, 2005
Mexico City, Mexico

Endorsed by the Association for Computational Linguistics (ACL)

Publication: Springer LNCS, vol. 3406.
Deadline: full papers: October 10, short papers: October 20
Keynote speakers: Ellen Riloff, Kevin Knight, Christian Boitet, Daniel Marcu
Excursions: Ancient pyramids, Monarch butterflies, great cave, and more

 NEW:  PHOTOS

Abstracts of accepted papers - Awards

Table of Contents - Author Index - Final Program

Awards

Call For Papers

This conference is the sixth CICLing event. The past CICLing conferences have been very successful, according to the comments of the participants: Fantastic conference! (Martin Kay, 2004), Everything was just great! Super-hyper-ultra-well done! (Igor Mel'cuk, 2000). We consider the following factors to define our identity:

   Excellent keynote speakers. We invite the most prominent scientists of the field to give keynote talks which, unlike at many other confs, are published in extenso in the Proceedings. They also organize an additional tutorial or discussion, and usually even participate in the excursions, where you can speak with them in an informal environment. [Past participants' opinions]

   General interest. The conf covers nearly all topics related to computational linguistics. This makes it attractive for people from different areas and leads to vivid and interesting discussions and exchange of opinions.

   Informal interaction. It is intended for a small group of professionals, some 50 participants. This allows for informal and friendly atmosphere, more resembling a friendly party than an official event. At CICLing you can pass hours speaking with your favorite famous scientists who you scarcely could greet in the crowd at large confs.

   Excellent excursions. Mexico is a wonderful country rich in culture, history, and nature. The conference is intended for people feeling themselves young in their souls, adventurous explorers in both science and life. Our cultural program brings the participants to unique marvels of history and nature hidden from the ordinary tourists.

   Relief from frosts. In the middle of February frosts, the participants from Northern countries can enjoy bright warm sun under the shadow of palms.

The conf is held at the Center for Computer Research (CIC) of the National Polytechnic Institute (IPN), Mexico. The IPN is one of the largest universities in the world, with over 120,000 students. The CIC is a relatively new school devoted to the cutting edge research in all areas of science related to computers, both in software and hardware. The conf is organized by the Natural Language Processing laboratory of CIC (you can find some our publications at www.Gelbukh.com).

In general, we are interested in whatever helps, will help eventually, or might help computers meaningfully process language data.

The conference is intended to the exchange of opinions between the scientists working in different areas of the growing field of computational linguistics and intelligent text processing. Our idea is to get a general view of the state of art in computational linguistics and its applications.

Areas of interest include, but are not limited by, the following topics, as long as the topic is presented in computer-related or formal description aspects:

Computational linguistics research:

   Computational linguistic theories and formalisms

   Representation of linguistic knowledge

   Morphology

   Syntax

   Semantics

   Discourse models

   Ambiguity resolution

   Word Sense Disambiguation

   Anaphora resolution

   Text generation

   Machine translation

   Statistical methods in computational linguistics

   Corpus linguistics

   Lexical resources

Intelligent text processing and applications:

   Document classification and search

   Information retrieval

   Information extraction

   Text mining

   Automatic summarization

   Spell checking

   Natural language interfaces

Naturally, we welcome the works on processing any language, not necessarily English, though major languages are of more general interest. Note: when describing phenomena of languages other than English, please be sure to make your discussion understandable for people not familiar with this language.

You can have a look at the past CICLing-2004, 2003, 2002, 2001, 2000 tables of contents to get an idea of our interests. If you are not sure whether your particular topic is of interest, please do not hesitate to ask us.

   Ellen Riloff (U. Utah)

Formal presentation:  to be announced.

Informal discussion/event: to be announced.

   Kevin Knight (ISI)

Formal presentation: An Overview of Probabilistic Tree Transducers for Natural Language Processing (with Jonathan Graehl).

Informal discussion/event: to be announced.

   Christian Boitet (CLIPS-IMAG, Grenoble)

Formal presentation: tentatively: Message automata for messages with variants, and methods for their translation.

Informal discussion/event: to be announced.

   Daniel Marcu (ISI)

Formal presentation:  Probabilistic Generative Models for Natural Language Processing and Reasoning.

Informal discussion/event: to be announced.

[Past participants' opinions]

The camera-ready deadline is firm. We do not guarantee the inclusion of any paper that does not arrive (in camera-ready version) by the deadline indicated above.

Authors of rejected full papers may be given a chance to re-submit their works as short papers well before November 10.

If for some reason you contact us for late submission, please indicate a tentative title of your paper.

Authors of accepted papers: By submitting a paper, at least one author thereby promises, in case of acceptance of the paper, to attend the conf in person to present the paper and to pay the corresponding early registration fee. Unless the current policy changes, the authors of accepted papers will register on-site at the early registration rate. Note: We reserve the right to change this information before November 10; please check our website.

Public (not authors): For early registration information, please contact us before November 10.

The registration will be on site, in cash (US$ or Mexican pesos). All authors will pay early fee. Those of general public who did not arrange with us the payment of the early fee, will pay full fee. Please do not send us any money, unless otherwise is explicitly agreed with us.

Registration fee:

On reduced registration fee: A very limited number of reduced registrations may be available. To apply, please contact us and thoroughly justify your application. Eligible for reduced registration can be people from underdeveloped countries in case if their institutions have real difficulties paying the full fee (included: Latin America, Eastern Europe; not included: North America, Western Europe, Japan, South Korea). Authors must apply for reduced registration (clearly indicating the amount of reduction) at the moment of submission of their paper for review; no new applications will be considered for already reviewed papers. Notes: (1) Though all papers are judged by strictly academic criteria, only for borderline cases and only of papers of comparable quality we may give preference to papers with paid fee. (2) Though we will do our best for this not to happen, we cannot guarantee providing the conf material (including the Proceedings) and the conf lunch tickets to participants with reduced fee. Also, in case of lack of seats in the excursion bus we will give preference to fully registered participants.

Publication

All accepted full and short papers will be published in a Proceedings volume edited by Springer-Verlag in its Lecture Notes in Computer Science series.

The full papers should not exceed 12 pages, though we encourage you to keep it as short as possible (but not shorter!). If you really need more pages, please contact us.

Short papers should not exceed 4 pages and should, if possible, contain references to Internet sites where more detail on the work can be found. In all other respects the format of the short papers is identical to that of full papers.

Format

Please provide your paper in the form in which it should appear in the book (but without page numbers, running heads, and copyright note). Specifically, please do indicate the authors' names normally (we will take care of hiding them for blind review if needed).

If for some reason you really prefer to hide some information for blind review, please leave the exact space which it occupies. Or, just tell us to eliminate it from the PDF file before sending it to review.

Please strictly follow the format guidelines of Springer LNCS series (you can get the style files here). We cannot guarantee publication of any paper that does not follow these guidelines. Please do not hesitate to ask any questions.

The following are frequent formatting problems:

1.     Word users: Do not underline email addresses or URLs, and do not write them in blue font. See also below the notes on bugs in the Word template.

2.     All figures, tables, formulas, etc. must be within margins. We will not be able to include papers that do not meet this requirement.

3.     All pages must be free of page numbers and running heads.

4.     Please do not leave unused space on the pages. Try moving your figures if they cause unused space. Avoid if possible the last page being filled less than to 1/3.

5.     No section title should be the last line on the page. Avoid widow and orphan lines.

6.     The title and all section titles must be First Letter Capitalized.

7.     Figure captions must be below the figure; table captions must be above the table (especially important for TeX users). Both figures and tables should be centered.

8.     Do not use colors in figures: they will not be visible in paper book. Especially in Excel drawings, a blue and a red line will look equal, and a yellow line will not be visible at all. In Excel drawings, eliminate the outer frame, and make the background white (not grey), see below.

9.     For homogenous look of the book, please format the tables, whenever it does not cause difficulties in understanding the table, with only three thin horizontal lines: