Research Projects

TITLE OF THE PROJECT: EUROTERM: Extending the EuroWorNet with Public Sector Terminology.

REFERENCE: EuroTerm EDC-2214
FINANCE: eContent Programme
TIME:      FROM:    01/01/2001    TO:      30/06/2002
PROJECT LEADER: Dr. Manuel Palomar Sanz
MEMBERS: Dr. Antonio Ferrández, Armando Súarez, Dr.Patricio Martínez-Barco, Dr. Jesús Peral,
Dr. Rafael Muñoz, Maximiliano Saiz-Noeda, Andrés Montoyo, José Luis Vicedo, Fernando Llopis

PARTNERS:   - Databases Laboratory of Computer Engineering & Informatics Department of Patras University (Greece).
                        - CentER Applied Research, Tilburg University, Netherlands
                        - Departamento de Lenguajes y Sistemas Informáticos, Universidad de Alicante.

Current Information about the project.

TITLE OF THE PROJECT:“TUSIR: Desarrollo de un sistema de comprensión de textos aplicado a la recuperación de información”

REFERENCE: TIC2000-0664-C02-01/02
FINANCE: Comisión Interministerial de Ciencia y Tecnología (CICYT).
TIME:      FROM:    28/12/2000    TO:      27/12/2003
PROJECT LEADER: Dr. Manuel Palomar Sanz
MEMBERS: Dr. Antonio Ferrández, Armando Súarez, Dr.Patricio Martínez-Barco, Dr. Jesús Peral,
Dr. Rafael Muñoz, Maximiliano Saiz-Noeda, Andrés Montoyo, José Luis Vicedo, Fernando Llopis, Rafael Romero

PARTNERS: Universidad de Alicante y Universidad Politécnica de Valencia

TITLE OF THE PROJECT: Construcción de Analizadores Híbridos de Lenguajes Naturales
(Construction of Hybrid Analyzers for Natural Languages Defined in Constrained Semantic Domains)
REFERENCE: TIC97-0671-C02-02
FINANCE: Comisión Interministerial de Ciencia y Tecnología (CICYT).
TIME:      FROM:     01/08/1997     TO:      31/07/2000
PROJECT LEADER: Dr. Manuel Palomar Sanz
MEMBERS: Dr. Antonio Ferrández, Armando Súarez, Jaime Gómez, Patricio Martínez-Barco, Jesús Peral,
Rafael Muñoz, Maximiliano Saiz-Noeda.

SUMMARY OF THE PROJECT:
The development of systems for Natural Language processing has specific difficulties when we want to achieve
a wide coverage of the language. Some well characterised linguistic phenomena (anaphora, ellipsis,...), and the
phenomena characteristics of the spontaneous speech, which could produce syntactically incorrect sentences,
must be considered. These problems can be raised from a deductive point of view, through the design of a
language model from the linguistic knowledge, or can be raised through the application of inductive learning
techniques from data. On the other hand, attending to the output that the system must supply, one of
the most interesting possibility is that the system give us the meaning of the input sentences, in terms of a
semantic language. This kind of semantic output could be used in later processes (translation, execution
of actions, etc.). The main objective of this project is the development of language understanding systems
in semantically constrained tasks. We will develop different deductive methodologies of analysis, as it is
habitual in the Natural Language area, and some inductive learning techniques, which are successfully
used in the Automatic Speech Recognition area. The co-operation of these two approaches will allow us
to develop Natural Language processing systems more and more complex. The main aspects to be studied
are the estimation of statistic regular models and the construction of context-free grammars in order to
represent the characteristics of the language of the task, and the development of analyzers which supply
the semantic messages of the input sentences.

TITLE OF THE PROJECT: Development of a Corpus-based integrated anaphora resolution system for spanish and english.
REFERENCE: HB1998-0068 (Collaborative research project between Spain and The United Kingdom)
FINANCE: Ministerio de Educación y Cultura. Dir. Gral. de Enseñanza Superior e Investigación Científica.
TIME: FROM:     01/04/1999   TO:     1/03/2001
PROJECT LEADER: Dr. Manuel Palomar Sanz
MEMBERS: Dr. Antonio Ferrández, Dra. Lidia Moreno, Patricio Martínez-Barco, Jesús Peral, Rafael Muñoz,
Maximiliano Saiz-Noeda.

SUMMARY OF THE PROJECT:
The project will focus on the construction of a bilingual (Spanish, English) coreferentially annotated corpus and its exploita-tion
for the development and improvement of an integrated corpus-based anaphora resolution system for Spanish and English.
The new system will be built by combining key components of the anaphora resolution systems which have already been
developed by each of the partners (and which have demonstrated high success rates  - see Férrandez et al. 1998a;
Mitkov 1998b) and will benefit from the bilingual corpus with a view to achieving maximum performance.

The project will naturally combine the competence in anaphora resolution of the British and Spanish sides which each have
good experience in the field. The main contributions of the project can be seen in (i) the development of a new enhanced
multilingual (English and Spanish) anaphora resolution system and (ii) the construction of a coreferentially marked up
corpus for both Spanish and English which will be a novel resource