Welcome Message
from the Program Chair
CICLing-2002 is the third annual Conference on Intelligent Text Processing and Computational Linguistics (hence the name CICLing), see www.CICLing.org. It is intended to provide a balanced view of the cutting edge developments in both theoretical foundations of computational linguistics and practice of natural language text processing with its numerous applications.
At CICLing-2002, 35 talks and 13 short papers (posters) will be presented by the participants from 19 countries, in the order of number of authors: Spain, Mexico, Japan, UK, Israel, Germany, Italy, USA, Switzerland, Taiwan, Ireland, Australia, China, Czech Rep., France, Russia, Bulgaria, Poland, Romania. We are proud to announce the invited talks by Nicoletta Calzolari (Inst. for Computational Linguistics, Italy), Ruslan Mitkov (U. of Wolverhampton, UK), Ivan Sag (Stanford U., USA), Yorick Wilks (U. of Sheffield), and Antonio Zampolli (Inst. for Computational Linguistics, Italy). The conference will also feature four informal “discussion” events organized by these our guests.
On Monday, an informal event will be organized combining at the same time and in the same place a welcome party, poster presentations, and demonstrations. The participants will have about 3 hours to speak with each other and with local students in an informal atmosphere.
According to its name—Conference on Intelligent text processing and Computational LINGuistics—the conference will mainly focus on the following topics:
· Computational linguistics theories and formalisms;
· Specific issues in computational morphology, syntactic parsing, and semantics;
· Applications in information retrieval, document analysis, and text classification.
The conference will be mainly oriented to specialists in computational linguistics and text processing. At the same time it will give the novices the idea of the current problems and applications of both computational linguistics theory and the practice of natural language processing, as well as of the methods used in these areas. For the students, the conference will be a good introduction into the state of the art and the cutting edge of the current research in the area.
The conference will be held in Mexico, a marvelous country with rich culture, history, and nature. It will feature an extensive cultural program, including excursions to the most interesting tourist attractions—both archeological and natural—that can be reached within one day from Mexico City: solemn 2000-years-old pyramids of legendary Teotihuacán, a Monarch butterfly wintering site where the old pines are covered with millions of butterflies as if they were leaves, a great cave with 85-meter halls and a river flowing from it, Aztec warriors dancing in the street in their colorful plumages, and the largest anthropological museum of the world.
Welcome to Mexico! ¡Bienvenidos a México!
|
Sincerely,
Alexander Gelbukh, |
|
|
Program Chair of CICLing-2002
|
|
Sunday 17
Cultural events
|
09:00 |
Excursion to the Pyramids. Meeting point: hotel El Ejecutivo, reception |
|
19:30 |
Back to the hotel (approximate time) |
|
19:30 |
Informal excursion to City Center (only if there are any people interested; approximate time*) |
|
22:00 |
Back to the hotel (very approximate time) |
* The informal excursion is just a continuation of the main one, using the same bus. Please let me know in advance by email if you want to participate in this informal excursion, but you will not participate in the main excursion to the Pyramids.
Monday 18
Semantics. Anaphora and reference. Welcome party. Posters. Demos
|
08:30 |
Registration |
|
09:30 |
Inauguration Teresa Carbó |
|
10:00 |
Invited talk: |
|
|
Ruslan Mitkov, Richard Evans, and Constantin Orasan |
|
10:40 |
Pronominal anaphora generation in an English-Spanish MT approach |
|
|
Jesús Peral and Antonio Ferrández |
|
11:20 |
Break |
|
11:30 |
A hypothesis on the origin of the sign types |
|
|
Roland Hausser |
|
12:10 |
Multilayered extended semantic networks as a language for meaning representation in NLP systems |
|
|
H. Helbig and C. Gnörlich |
|
12:50 |
Dinner |
|
13:50 |
Constructing a sensuous judgment system based on conceptual processing |
|
|
Atsushi Horiguchi, Seiji Tsuchiya, Kazuhide Kojima, Hirokazu Watabe,and Tsukasa Kawaoka |
|
14:30 |
Towards a natural language driven automated help desk |
|
|
Melanie Knapp and Jens Woch |
|
15:10 |
Break |
|
15:20 |
The Spanish auxiliary verb system in hpsg |
|
|
Ivan Meza and Luis Pineda |
|
16:00 |
Automatic generation of pronunciation lexicons for Spanish |
|
|
Esmeralda Uraga and Luis Pineda |
|
16:40 |
Break: preparation of posters by the presenters |
|
17:00 |
Welcome party. Posters. Demos |
|
|
See the list of posters and demos at the end of this Program |
|
19:00 |
End of Monday program (approximate time) |
Tuesday 19
Parsing techniques. Word sense disambiguation.
|
09:00 |
Invited
talk: |
|
|
Yorick Wilks and Roberta Catizone |
|
09:40 |
A baseline methodology for word sense disambiguation |
|
|
Ted Pedersen |
|
10:20 |
Combining supervised-unsupervised methods for word sense disambiguation |
|
|
Andrés Montoyo, Armando Suárez, and Manuel Palomar |
|
11:00 |
Break |
|
11:10 |
An adapted Lesk algorithm for word sense disambiguation using WordNet |
|
|
Satanjeev Banerjee and Ted Pedersen |
|
11:50 |
Feature selection analysis for maximum entropy-based WSD |
|
|
Armando Suárez and Manuel Palomar |
|
12:30 |
Parsing ill-formed inputs with constraint graphs |
|
|
Philippe Blache and David-Olivier Azulay |
|
13:10 |
Dinner |
|
14:10 |
Diacritics restoration: learning from letters versus learning from words |
|
|
Rada F. Mihalcea |
|
14:50 |
Part-of-speech tagging with evolutionary algorithms |
|
|
Lourdes Araujo |
|
15:30 |
Formal methods of tokenization for part-of-speech tagging |
|
|
Jorge Graña, Fco. Mario Barcala,and Jesús Vilares |
|
16:10 |
Break |
|
16:20 |
Sepe: A POS tagger for Spanish |
|
|
Héctor Jiménez and Guillermo Morales |
|
17:00 |
Invited unpublished
event: |
|
|
Yorick Wilks |
|
18:00 |
End of Tuesday program (approximate time) |
Wednesday 20
Cultural events
|
07:00 |
Excursion to Butterflies (main excursion). Meeting point: hotel El Ejecutivo, reception |
|
23:30 |
Back to hotel |
In parallel with the main excursion to the Butterflies, an additional excursion can be organized if there are people interested in it (and not interested in the main one), though we recommend the main one.
|
10:00 |
Excursion to City Center (additional excursion) |
|
18:00 |
Back to hotel (very approximate time) |
Thursday 21
Dictionaries and corpora. Document processing and IR.
|
09:00 |
To be confirmed. If this talk is cancelled then Thursday program begins at 09:40. The participants will be notified on or before Tuesday. Invited talk: |
|
|
Nicoletta Calzolari, Antonio Zampolli, and Alessandro Lenci |
|
09:40 |
Invited
talk: |
|
|
Ivan A. Sag, Timothy Baldwin, Francis Bond, Ann Copestake, and Dan Flickinger |
|
10:20 |
Cross-lingual document similarity calculation using the multilingual thesaurus Eurovoc |
|
|
Ralf Steinberger, Bruno Pouliquen,and Johan Hagman |
|
11:00 |
Break |
|
11:10 |
Aligning multiword terms using a hybrid approach |
|
|
Arantza Casillas and Raquel Martínez |
|
11:50 |
Integrated natural language generation with schema–tree adjoining grammars |
|
|
Karin Harbusch and Jens Woch |
|
12:30 |
A computational model of change in politeness with the addition of word endings |
|
|
Tamotsu Shirado and Hitoshi Isahara |
|
13:10 |
Dinner |
|
14:10 |
A comparative study of information extraction strategies |
|
|
Ronen Feldman, Yonatan Aumann, Michal Finkelstein-Landau, Eyal Hurvitz, Yizhar Regev,and Ariel Yaroshevich |
|
14:50 |
Answer extraction in technical domains |
|
|
Fabio Rinaldi, Michael Hess, Diego Mollá, Rolf Schwitter, James Dowdall, Gerold Schneider, and Rachel Fournier |
|
15:30 |
Text segmentation for efficient information retrieval |
|
|
Fernando Llopis, Antonio Ferrández and José Luis Vicedo |
|
16:10 |
Break |
|
16:20 |
Using syntactic dependency-pairs conflation to improve retrieval performance in Spanish |
|
|
Jesús Vilares, Fco. Mario Barcala,and Miguel A. Alonso |
|
17:00 |
Multi-document summarization using informative words and its evaluation with a QA system |
|
|
June-Jei Kuo, Hung-Chia Wung, Chuan-Jie Lin,and Hsin-Hsi Chen |
|
17:40 |
Empirical formula for testing word similarity and its application for constructing a word frequency list |
|
|
Pavel Makagonov and Mikhail Alexandrov |
|
18:20 |
Break |
|
18:30 |
To be confirmed. If this talk is cancelled then Thursday program ends at 18:20. Chinese document classification based on N-grams. |
|
|
Shuigeng Zhou and Jihong Guan |
|
19:10 |
End of Thursday program |
Friday 22
Cultural events. Discussions
|
08:30 |
Excursion to the Anthropological Museum. Meeting point: hotel El Ejecutivo, reception; return: CIC (conf site). |
|
13:00 |
Dinner |
|
14:00 |
Invited
unpublished event: |
|
|
Ruslan Mitkov |
|
14:45 |
Surface syntactic relations in Spanish |
|
|
Igor A. Bolshakov |
|
15:20 |
Sign language translation via drt and hpsg |
|
|
Éva Sáfár and Ian Marshall |
|
16:00 |
Break |
|
16:10 |
Invited
unpublished event: |
|
|
Ivan A. Sag |
|
17:20 |
Break |
|
17:30 |
To be confirmed. If this talk is cancelled then the closure of conference is at 17:20. Invited unpublished event: |
|
|
Nicoletta Calzolari, Antonio Zampolli |
|
18:30 |
Closure of the conference |
Cultural events
|
08:30 |
Excursion to the cave and Taxco city. Meeting point: hotel El Ejecutivo, reception |
|
22:00 |
Back to hotel |
Posters and demos
All posters will be presented on Monday at 17:00 to 19:00
1. A proposal for WSD using semantic similarity
Susana Soler and Andrés Montoyo
2. Fuzzy set tagging
Dariusz J. Kogut
3. Quantitative comparison of homonymy in Spanish EuroWordNet and traditional dictionaries
Igor A. Bolshakov, Sofia N. Galicia-Haro,and Alexander Gelbukh
4. Automatic selection of defining vocabulary in an explanatory dictionary
Alexander Gelbukh and Grigori Sidorov
5. Compilation of a Spanish representative corpus
Alexander Gelbukh, Grigori Sidorov, and Liliana Chanona-Hernández
6. Experiments with a bilingual document generation environment
Arantza Casillas and Raquel Martínez
7. Tatar morphological implementation
Dj. Sh. Suleymanov
8. Automatic extraction of non-standard lexical data for a metalinguistic information database
Carlos Rodríguez
9. Automated selection of interesting medical text documents by the TEA text analyzer
Jan Žižka and Aleš Bourek
10. AutoMarkup: A tool for automatically marking up text documents
Shazia Akhtar, Ronan G. Reilly,and John Dunnion
11. Recurrent patterns in definitory context
Gerardo Sierra and Rodrigo Alarcón
12. Specification marks method: design and implementation
Sonia Vázquez, Ma Carmen Calle, Susana Soler and Andrés Montoyo