Computational Linguistics and Intelligent Text Processing
Final Schedule
Changes in comparison with the preliminary schedule:
(1) Time and duration of many talks are changed. Check the time of your talk!
(2) Topics of Adam Kilgarriff’s talk and Friday invited discussions are announced.
(3) Cancelled:
Formal Representation and Semantics of Modern Chinese Interrogative Sentences
Jia-ju Mao, Qiu-lin Chen, Ru-zhan Lu
Analyzing V+Adj in Situation Semantics
Jia-ju Mao, Qiu-lin Chen, Ru-zhan Lu
An Efficient Online Parser for Contextual Grammars with at Most Context-Free Selectors
Karin Harbusch
QGen — Generation Module for the Register Restricted InBASE System
Michael V. Boldasov and Elena G. Sokolova
Using Natural Language Processing for Semantic Indexing of Scene-of-Crime Photographs
Horacio Saggion and Katerina Pastra and Yorick Wilks
Experimental Study on Representing Units in Chinese Text Categorization
Li Baoli, Chen Yuzhong, Bai Xiaojing, Yu Shiwen
An Estimate Method of the Minimum Entropy of Natural Languages
Fuji Ren, Shunji Mitsuyoshi, Kang Yen, Chengqing Zong, Hongbing Zhu
Word Sense Disambiguation for Untagged Corpus: Application to Romanian Language
Gabriela Şerban and Doina Tătar
Automatic Text Summarization of Scientific Articles Based on Classification of Extract's Population
Maher Jaoua and Abdelmajid Ben Hamadou
(4) Moved to another day (and might be cancelled later):
Performance Analysis of a Part of Speech Tagging Task
Rada Mihalcea
All excursions depart from the official hotel of the conf (El Ejecutivo, to be confirmed!) and return to it.
Each working day of the conf, there will be transportation between the hotel and the conf place, see the schedule below.
Each of the four invited speakers will present both a formal talk (see the schedule) and an informal event on Friday.
All posters and demos will be presented on Monday evening and also can be discussed during the rest of the conf.
|
|
|
|
Sunday |
|
|
|
|
|
09:00–19:30 |
Excursion to the Pyramids (bus at the hotel). Informal discussions. |
|
19:30–22:00 |
Informal excursion to the City Center (if there are any people interested). Bus from the main excursion passes by the hotel (approximate time). |
|
|
|
|
Monday |
|
|
|
|
|
08:10 |
Bus at the hotel |
|
08:40–09:25 |
Registration |
|
09:30–10:00 |
Inauguration |
|
|
Computational Linguistics Formalisms |
|
10:00–11:00 |
Keynote talk: Starting with Complex Primitives Pays Off Aravind K. Joshi |
|
11:00–11:35 |
Things Are Not Always Equal Ronald M. Kaplan and Annie Zaenen |
|
11:35–11:45 |
Break |
|
11:45–12:20 |
Computing with Realizational Morphology Lauri Karttunen |
|
12:20–12:50 |
Positive Grammar Checking: A Finite State Approach Sylvana Sofkova Hashemi, Robin Cooper and Robert Andersson |
|
12:50–13:50 |
Lunch |
|
13:50–14:15 |
GIGs: Restricted Context-sensitive Descriptive Power in Bounded Polynomial-time José M. Castaño |
|
14:15–14:40 |
Total Lexicalism and GAS Grammars: A Direct Way to Semantics Gábor Alberti and Katalin Balogh and Judit Kleiber and Anita Viszket |
|
|
Semantics and Discourse |
|
14:40–15:05 |
Imperatives as Obligatory and Permitted Actions Miguel Pérez-Ramírez, Chris Fox |
|
15:05–15:15 |
Break |
|
15:15–15:40 |
Diagnostics for Determining Compatibility in English Support-verb-nominalization Pairs Leslie Barrett and Anthony R. Davis |
|
15:40–16:05 |
A Maximum Entropy Approach for Spoken Chinese Understanding Guodong Xie, Chengqing Zong, Bo Xu |
|
16:05–16:30 |
A Study to Improve the Efficiency of a Discourse Parsing System Huong T. Le, Geetha Abeysinghe |
|
16:30–17:00 |
Break; authors of the posters put their material |
|
17:00–19:00 |
Welcome party (wine and light food) Posters, demos (see the list of posters below) |
|
19:10 |
Bus to the hotel |
|
|
|
|
Tuesday |
|
|
|
|
|
08:10 |
Bus at the hotel |
|
|
Syntax and POS tagging |
|
09:00–09–25 |
Conversion of Japanese Passive/Causative Sentences into Active Sentences Using Machine Learning Masaki Murata and Hitoshi Isahara |
|
09:25–09:45 |
From Czech Morphology through Partial Parsing to Disambiguation Eva Mráková and Radek Sedláček |
|
09:45–10:10 |
Fast Base NP Chunking with Decision Trees — Experiments on Different POS Tag Settings Dirk Lüdtke and Satoshi Sato |
|
10:10–10:35 |
Guaranteed Pre-Tagging for the Brill Tagger Saif Mohammad and Ted Pedersen |
|
10:35–10:45 |
Break |
|
|
Parsing Techniques |
|
10:45–11:10 |
Off-line Compilation of Chains for Head-driven Generation with Constraint-based Grammars Toni Tuells, German Rigau, Horacio Rodríguez |
|
11:10–11:35 |
Generation of Incremental Parsers Manuel Vilares, Miguel A. Alonso, and Victor M. Darriba |
|
|
Word Sense Disambiguation |
|
11:35–12:05 |
Automatic Sense Disambiguation of the Near-Synonyms in a Dictionary Entry Diana Zaiu Inkpen and Graeme Hirst |
|
12:05–13:05 |
Keynote talk: Using Measures of Semantic Relatedness for Word Sense Disambiguation Siddharth Patwardhan, Satanjeev Banerjee and Ted Pedersen |
|
13:05–14:05 |
Lunch |
|
14:05–15:05 |
Keynote talk: Web as corpus Adam Kilgarriff |
|
|
Dictionary, Lexicon, Ontology |
|
15:05–15:35 |
Augmenting WordNet's Structure Using LDOCE Vivi Nastase and Stan Szpakowicz |
|
15:35–16:05 |
Is Shallow Parsing Useful for Unsupervised Learning of Semantic Clusters? Marie-Laure Reinberger and Walter Daelemans |
|
16:05–16:15 |
Break |
|
16:15–16:35 |
Experiments on Extracting Semantic Relations from Syntactic Relations Caroline Varaschin Gasperin and Vera Lúcia Strube de Lima |
|
16:35–17:00 |
Dimensional Analysis to Clarify Relations among the Top-Level Concepts of an Upper Ontology: Process, Event, Substance, Object Patrick Cassidy |
|
17:00–17:25 |
Classifying Functional Relations in Factotum via WordNet Hypernym Associations Tom O'Hara and Janyce Wiebe |
|
|
Speech Processing |
|
17:25–17:50 |
Chinese Utterance Segmentation in Spoken Language Translation Chengqing Zong and Fuji Ren |
|
18:00 |
Bus to the hotel |
|
|
|
|
Wednesday |
|
|
|
|
|
07:00–23:30 |
Excursion to the Butterfly Wintering site (bus at the hotel). Informal discussions. |
|
|
|
|
Thursday |
|
|
|
|
|
09:10 |
Bus at the hotel |
|
|
Corpus and Language Statistics |
|
10:00–11:00 |
Keynote talk: Processing Natural Language without Natural Language Processing Eric Brill |
|
11:00–11:30 |
The Design, Implementation and Use of the Ngram Statistics Package Satanjeev Banerjeet and Ted Pedersen |
|
11:30–12:00 |
Performance Analysis of a Part of Speech Tagging Task Rada Mihalcea |
|
12:00–12:10 |
Break |
|
12:10–12:40 |
A Corpus Balancing Method for Language Model Construction Luis Villaseñor-Pineda, Manuel Montes-y-Gómez, Manuel Alberto Pérez‑Coutiño, and Dominique Vaufreydaz |
|
|
Machine Translation and Bilingual Corpora |
|
12:40–13:10 |
The Word is Mightier than the Count: Accumulating Translation Resources from Parsed Parallel Corpora Stephen Nightingale and Hideki Tanaka |
|
13:10–13:40 |
Identifying Complex Sound Correspondences in Bilingual Wordlists Grzegorz Kondrak |
|
13:40–14:40 |
Lunch |
|
|
Text Generation |
|
14:40–15:10 |
Generating Texts with Style Richard Power, Donia Scott, and Nadjet Bouayad-Agha |
|
15:10–15:40 |
Multilingual Syntax Editing in GF Janna Khegai, Bengt Nordström, and Aarne Ranta |
|
|
Natural Language Interfaces |
|
15:40–16:10 |
Towards Designing Natural Language Interfaces Svetlana Sheremetyeva |
|
16:10–16:40 |
A Portable Natural Language Interface for Diverse Databases Using Ontologies J. Antonio Zárate M., Rodolfo A. Pazos R., Alexander Gelbukh, and J. Isabel Padrón C. |
|
16:40–16:50 |
Break |
|
|
Information Retrieval and Information Extraction |
|
Natural Language System for Terminological Information Retrieval Gerardo Sierra and John McNaught |
|
|
17:10–17:40 |
Probabilistic Word Vector and Similarity based on Dictionaries Satoshi Suzuki |
|
17:40–18:00 |
Web Document Indexing and Retrieval Byurhan Hyusein and Ahmed Patel |
|
|
Text Categorization and Summarization |
|
18:00–18:20 |
A Study on Feature Weighting in Chinese Text Categorization Xue Dejun, Sun Maosong |
|
18:20–18:40 |
CANCELLED Automatic Text Summarization of Scientific Articles Based on Classification of Extract's Population Maher Jaoua and Abdelmajid Ben Hamadou |
|
18:30 |
Bus to the hotel (CHANGED FROM 18:50) |
|
|
|
|
Friday |
|
|
|
|
|
08:40–12:40 |
Excursion to the Anthropological Museum (bus at the hotel). Bus from the museum to the hotel at 12:20. Informal discussions. |
|
12:40 |
Bus from the excursion passes by the hotel and goes to the conf place |
|
13:30–14:30 |
Lunch |
|
14:30–15:30 |
Discussion, topic to be announced Eric Brill |
|
15:30–16:30 |
Discussion on Discourse Structure Aravind Joshi |
|
16:30–16:40 |
Break |
|
16:40–17:40 |
Discussion: GRASHLs: grammatical, statistical, hierarchical lexicons Adam Kilgarriff |
|
17:40–18:40 |
Discussion:Word Sense Disambiguation, A Kitchen Sink Problem Ted Pedersen In this discussion I will survey a few of the many possible approaches to WSD. This will include supervised learning from sense-tagged text, dictionary based methods, and unsupervised clustering approaches from raw corpora. [Title taken from the expression, "I threw everything at that problem except the kitchen sink"] |
|
18:40–18:45 |
Closure |
|
18:55 |
Bus to the hotel |
|
|
|
|
Saturday |
|
|
|
|
|
08:10–22:00 |
Excursion to Xochicalco pyramids, Cacauhamilpa cave, and Taxco – colonial city (bus at the hotel). Informal discussions. |
Posters and demos
(Monday 17:00–19:00)
|
1. |
Pseudo Context-Sensitive Models for Parsing Isolating Languages: Classical Chinese – A Case Study Liang Huang, Yinan Peng, Zhenyu Wu, Zhihao Yuan, Huan Wang, and Hui Liu |
|
2. |
Approach to Construction of Automatic Morphological Analysis Systems for Inflective Languages with Little Effort Alexander Gelbukh and Grigori Sidorov |
|
3. |
Per-Node Optimization of Finite-State Mechanisms for Natural Language Processing Alexander Troussov, Brian O'Donovan, Seppo Koskenniemi, and Nikolay Glushnev |
|
4. |
Automatic Noun Sense Disambiguation Paolo Rosso, Francesco Masulli, Davide Buscaldi, Ferran Pla, and Antonio Molina |
|
5. |
Tool for Computer-Aided Spanish Word Sense Disambiguation Yoel Ledo Mezquita, Grigori Sidorov, and Alexander Gelbukh |
|
6. |
Building Consistent Dictionary Definitions Karel Pala and Eva Mráková |
|
7. |
A Method of Automatic Detection of Lexical Relationships using a Raw Corpus Héctor Jiménez-Salazar |
|
8. |
Sentence Co-occurrences as Small-world Graphs: A Solution to Automatic Lexical Disambiguation Stefan Bordag |
|
9. |
Building a Chinese Shallow Parsed TreeBank for Collocation Extraction Li Baoli, Lu Qin, Li Yin |
|
10. |
Corpus Construction within Linguistic Module of City Information Dialogue System Roman Mouček, Kamil Ekštein |
|
11. |
Diachronic Stemmed Corpus and Dictionary of Galician Language Nieves R. Brisaboa, Juan-Ramón López, Miguel R. Penabad, Ángeles S. Places |
|
12. |
Can We Correctly Estimate the Total Number of Pages in Google for a Specific Language? Igor A. Bolshakov and Sofia N. Galicia-Haro |
|
13. |
A Discourse System for Conversational Characters Ron Zacharski |
|
14. |
Time-Domain Structural Analysis of Speech Kamil Ekštein and Roman Mouček |
|
15. |
Experiments with Linguistic Categories for Language Model Optimization Arantza Casillas, Amparo Varona, Ines Torres |
|
16. |
Natural Language in Information Retrieval Elżbieta Dura |
|
17. |
Query Expansion based on Thesaurus Relations: Evaluation over Internet Luiz Augusto Sangoi Pizzato and Vera Lúcia Strube de Lima |
|
18. |
Suggesting Named Entities for Information Access Enrique Amigó, Anselmo Peñas, Julio Gonzalo, and Felisa Verdejo |
|
19. |
Event Sentence Extraction in Korean Newspapers Bo-Hyun Yun, Tae-Hyun Kim, Yi-Gyu Hwang, Pal-Jin Lee, and Seung‑Shik Kang |
|
20. |
Searching for Significant Word Associations in Text Documents Using Genetic Algorithms Jan Žižka and Michal Šrédl and Aleš Bourek |
|
21. |
Cascaded Feature Selection in SVMs Text Categorization Takeshi Masuyama and Hiroshi Nakagawa |
|
22. |
Partitional Clustering Experiments with News Documents Arantza Casillas and Mayte González de Lena and Raquel Martínez |
|
23. |
Fast Clustering Algorithm for Information Organization Kwangcheol Shin and Sangyong Han |