DETAILED PROGRAM ESTAL 2004

Wednesday, October 20th

8:30

Conference Registration (Registration desk)

9:15

Session 1: Machine Translation & Translation Aids

Chair: Nuno Mamede

"Automatic Acquisition of Transfer Rules from Translation Examples"
Werner Winiwarter

"SisHiTra: A hybrid machine translation system from Spanish to Catalan"
José Ramón Navarro, Jorge González, David Picó, Francisco Casacuberta, Joan Miquel de Val, Ferran Fabregat, Ferran Pla, Jesús Tomás

"Bayes Decision Rules and Confidence Measures for Statistical Machine Translation"
Nicola Ueffing, Hermann Ney

10:30

Opening Talk

10:45

Coffee break

11:15

Invited Talk: Walter Daelemans (University of Antwerp / Tilburg University)

Reusable Text Analysis for Applications

12:15

Session 2: Information Retrieval

Chair: Alfonso Ureña

"Spelling Correction for Search Engine Queries"
Bruno Martins, Mário Silva

"One Size Fits All? A Simple Technique to Perform Several NLP Tasks"
Daniel Gayo, Darío Álvarez, José Gay

“The merging problem in Distributed Information Retrieval and the 2-step RSV merging Algorithm."
Fernando Martínez Santiago, Miguel Ángel García Cumbreras, Alfonso Ureña

13:30

Lunch: “La Traviata” Restaurant

15:30

Poster Session

Chair: Rafael Muñoz

"Automatic Assessment of Open Ended Questions with a BLEU-inspired Algorithm and shallow NLP"
Enrique Alfonseca, Diana Perez

"Reuse of the free online translators to develop a meta-system of multilingual machine translation"
Hung VO TRUNG

"Information Retrieval in Digital Theses Based on Natural Language Processing Tools"
Rocio Abascal, Béatrice Rumpler, Jean-Marie Pinon

"Multiword Expression Translation Using Generative Dependency Grammar"
Stefan Diaconescu

"A Statistical Study of the WPT-03 Corpus"
Bruno Martins, Mário Silva

"Baseline Methods for Automatic Disambiguation of Abbreviations in Jewish Law Documents"
Yaakov HaCohen-Kerner, Ariel Kass, Ariel Peretz

"Expressive Power and Consistency Properties of State-of-the-Art Natural Language Parsers"
Gabriel Infante-Lopez, Maarten de Rijke

16:30

Session 3: Document Categorization (I)

Chair: Jose A. Troyano

"Multi-label text classification using multinomial models"
David Vilar, María José Castro, Emilio Sanchís

"On Word Frequency Information and Negative Evidence in Naive Bayes Text Classification"
Karl-Michael Schneider

17:20

Coffee break

17:45

Session 4: Document Categorization (II)

Chair: Walter Daelemans

"Adaptive selection of base classifiers in one-against-all learning for large multi-labeled collections"
Arturo Montejo-Ráez, Luís Alfonso Ureña-López, Ralf Steinberger

"Ontology-Based Feature Transformations: A Data-Driven Approach"
Filip Ginter, Sampo Pyysalo, Jorma Boberg, Jouni Jarvinen, Tapio Salakoski

"Using Seed Words to Learn to Categorize Chinese Text"
Jingbo Zhu, Wenliang Chen, Tianshun Yao

19:00

 

21:00

Welcome Reception

Casino de Alicante (Old Casino of Alicante)

Sponsored by Excmo. Ayuntamiento de Alicante  (City Hall of Alicante).

Thursday, October 21st

9:00

Session 5: Information extraction, QA & Summarization

Chair: Werner Winiwarter

"A study of chunk-based and keyword-based approaches for generating headlines"
Enrique Alfonseca, José María Guirao, Antonio Moreno-Sandoval

"Named Entity Recognition through Corpus Transformation and System Combination"
José A. Troyano, Vicente Carrillo, Fernando Enríquez, Francisco J. Galán

"Intertwining Deep Syntactic Processing and Named Entity Detection"
Caroline Brun, Caroline Hagège

"Comparison and evaluation of two approaches of a Multilayered QA system applied to Temporality"
Estela Saquete, Rafael Muñoz, Patricio Martinez-Barco, Jose Luis Vicedo

10:45

Coffee break

11:15

Invited Talk: Rada Mihalcea (University of North Texas)

Graph-Theory meets Computational Linguistics: Text Processing with Graph-based Ranking Algorithms

12:15

Session 6: NLP-based Applications

Chair: Caroline Brun

"An Independent Domain Dialogue System Through a Service Manager"
Márcio Mourão, Renato Cassaca, Nuno Mamede

"Automatic Spelling Correction in Galician"
Manuel Vilares, Juan Otero, Francisco Mario Barcala, Eva Domínguez

"On the Quality of Lexical Resources for Word Sense Disambiguation"
Lluis Marquez, Mariona Taule, Lluis Padro, Luis Villarejo, Maria Antonia Marti

13:30

Lunch

“La Traviata” Restaurant

15:30

Session 7: Word Sense Disambiguation

Chair: Rada Mihalcea

"Smoothing and Word Sense Disambiguation"
Eneko Agirre, David Martinez

"Significance of Syntactic Features for Word Sense Disambiguation"
Sasi Kanth Ala, Narayana Murthy Kavi

"Integrating Conceptual Density with WordNet Domains and CALD Glosses for Noun Sense Disambiguation"
Davide Buscaldi, Paolo Rosso, Francesco Masulli

16:45

Coffee break

17:15

Session 8: Spoken and Written Language Analysis & Generation

Chair: Peter Greenfield

"Automatic phonetic alignment and its confidence measures"
Sérgio Paulo, Luís Caldas de Oliveira

"The Contents and Structure of the Context Base, and its Application"
Yusuke Takahashi, Ichiro Kobayashi, Michiaki Iwazume, Noriko Ito, Michio Sugeno

"Suffixal and Prefixal Morpholexical Relationships of the Spanish"
Octavio Santana, José R. Pérez, Francisco J. Carreras, Gustavo Rodríguez

18:30

 

20:30

Bus to Castillo de Santa Bárbara

Departure from Plaza del Mar

21:00

Banquet Dinner

Castillo de Santa Bárbara

(Santa Bárbara Castle)

Friday, October 22nd

9:00

Session 9: Corpus-based & Statistical Language Modeling

Chair: Arturo Montejo

"SemRol: Recognition of Semantic Roles"
Paloma Moreda, Manuel Palomar, Armando Suarez

"Unsupervised training of a finite-state sliding-window part-of-speech tagger"

Enrique Sánchez-Villamil, Mikel L. Forcada, Rafael C. Carrasco

"Developing Competitive HMM PoS Taggers Using Small Training Corpora"
Muntsa Padró, Lluís Padró

"Exploring the Use of Target-Language Information to Train the Part-of-Speech Tagger of Machine Translation Systems"
Felipe Sánchez-Martínez, Juan Antonio Pérez-Ortiz, Mikel L. Forcada

"Language Understanding using n-multigram models"
Lluis F. Hurtado, Encarna Segarra, Fernando Garcia, Emilio Sanchis

11:05

Coffee break

11:30

Session 10: Pragmatics, Discourse, Semantics, Syntax & Morphology

Chair: Maximiliano Saiz-Noeda

"Semantic-aided anaphora resolution in Large Corpora development"
Maximiliano Saiz-Noeda, Borja Navarro, Rubén Izquierdo

"Character Identification in Children's Stories"
Nuno Mamede, Pedro Chaleira

"Developing a Minimalist Parser for Free Word Order Languages with Discontinuous Constituency"
Asad Sayeed, Stan Szpakowicz

"A multi-use incremental syntax-semantic interface"
Luísa Coheur, Nuno Mamede, Gabriel G. Bès

"Systemic analysis applied to problem solving: the case of the past participle in French"
Séverine Vienney, Sylviane Cardey, Peter Greenfield

13:35

Conference Closing

13:45