» REXIN: Developing An Extraction And Retrieval Multilingual Information System Using Web Interface

See full content »

From January 1, 2004 to December 31, 2004
Code: FIT-340100-2004-14
Funding: Ministry of Science and Technology (PROFIT Project)
Participating entities: University of Alicante and University of Jaén
Coordinator: Mecanización de Empresas, S.A.

Automatic information extraction from notarial deeds and storage on an electronic device as a database.

» Developing Systems For Multilingual Information Retrieval: Techniques And Tools

See full content »

From December 1, 2003 to November 30, 2006
Code: TIC2003-07158-C04
Funding: Ministry of Science and Technology
Participating entities: University of Jaén
Coordinator: L. Alfonso Ureña López

» Designing an across-the-web Multilingual Information Retrieval System

See full content »

From January 1, 2003 to December 31, 2003
Code: FIT-150500-2003-412
Funding: Ministry of Science and Technology
Participating entities: University of Jaén, University of Alicante and University of Sevilla
Coordinator: L. Alfonso Ureña López

» R2D2: Recovery Responses In Scanned Documents

See full content »

From December 1, 2003 to November 30, 2006
Code: TIC2003-07158-C04
Funding: Ministry of Science and Technology (CYCIT Project)
Participating entities:
Coordinator: Manuel Palomar Sanz

The main aim of the project is the evaluation and development of question-answering systems and the retrieval of documents in multilingual scenarios. For this, two main lines of action are proposed: The organization of the multilingual evaluation international campaign (CLEF) with the aim of proposing new criteria and tasks related to access to information both for assessing multilingual access systems and for studying the interactive aspects of such tasks. Also, the development of information access systems (Question-Answering Systems and Document Retrieval) by studying firstly the multilingual and interactive aspects, and secondly the robustness of the systems in written documents and transcripts.

» SRIM PROJECT

See full content »

From July 1, 2002 to December 31, 2003
Code: FIT-150500-2002-416 and FIT-150500-2003-412
Funding: Ministry of Science and Technology (PROFIT Project)
Participating entities: University of Jaén, University of Alicante
Coordinator: Dr. Antonio Ferrández Rodríguez

» LLaJú: Multilingual Information Retrieval

See full content »

LlaJú is a Multilingual Information Retrieval system based on statistical techniques. The demonstration implemented here is designed to operate on five languages belonging to the European Community, from a query necessarily expressed in the English language. The search will be carried out on documents written in German, Spanish, French, English and Italian. The indexed corpus is composed of more than one million news items published in 1994 in various newspapers and newswire agencies (Der Spiegel, EFE, Le Mode, Los Angeles Times, La Stampa, etc). The queries should be in English and will be translated into different languages.

» WSD: Semantic Disambiguation in English

See full content »

SINAI WSD is a system of Semantic Disambiguation in English based on neural networks. The network used is the LVQ trained with different linguistic resources such as Wordnet and Semcor. The convention to be followed for labeling is: word\POS#SENSE, where word is the original word, the POS is the Part Of Speech (1 if it is a name, 2 if it is a verb, 3 an adjective and 4 an adverb) and SENSE is the number of senses in WordNet 1.7. As this server is shared and contains other projects, the tagger is limited to the 1500 most common English words, in order to reduce resources.