Luís Fernando Costa

SWING: an integrated environment for geospatial semantic web services

Geospatial Web services allow to access and to process Geospatial data. Despite significant standardisation efforts, severe heterogeneity and interoperability problems remain. The SWING environment leverages the Semantic Web Services (SWS) paradigm to address these problems. The environment supports the entire life-cycle of Geospatial SWS. To this end, it integrates a genuine end-user tool, a tool for developers of new Geospatial Web services, a commercial service Catalogue, the Web Service Execution Environment platform (WSMX), as well as an annotation tool. The demonstration includes three usage scenarios of increasing complexity, involving the semantic annotation of a legacy service, the semantic discovery of a Geospatial SWS, as well as the composition of a new Geospatial SWS.

Cooperatively evaluating portuguese morphology

This paper describes the first attempt to evaluate morphological analysers for Portuguese with an evaluation contest. It emphasizes the options that had to be taken and that highlight considerable disagreement among the participating groups. It describes the trial intended to prepare the real contest in June 2003, its goals and preliminary results.

First evaluation of esfinge: a question answering system for portuguese

This paper starts by describing Esfinge, a general domain Portuguese question answering system that uses the redundancy available in the Web as an important resource to find its answers. The paper also presents the strategies employed to participate in CLEF-2004 and discusses the results obtained. Three different strategies were tested: searching the answers only in the CLEF document collection, searching the answers in the Web and using the CLEF document collection to confirm these answers and finally searching the answers only in the Web. The intriguing question of why the system performed better when joining the two information sources, even though it was designed for the Web is discussed; in this connection, different language varieties and some problems of Google are mentioned. The paper concludes describing some of the work planned for the near future.

20th century esfinge (sphinx) solving the riddles at CLEF 2005

Esfinge is a general domain Portuguese question answering system. It tries to take advantage of the steadily growing and constantly updated information freely available in the World Wide Web in its question answering tasks. The system participated last year for the first time in the monolingual QA track. However, the results were compromised by several basic errors, which were corrected shortly after. This year, Esfinge participation was expected to yield better results and allow experimentation with a Named Entity Recognition System, as well as try a multilingual QA track for the first time. This paper describes how the system works, presents the results obtained by the official runs in considerable detail, as well as results of experiments measuring the import of different parts of the system, by reporting the decrease in performance when the system is executed without some of its components/features.

Question answering beyond CLEF document collections

Esfinge is a general domain Portuguese question answering system, which uses the information available in the Web as an additional resource when searching for answers. The experiments described in this paper show that the Web helped more with this years questions than in previous years and that using the Web to support answers also enables the system to answer correctly or at least to find relevant documents for more questions. In this third participation in CLEF, the main goals were (i) to check whether a database of word cooccurrences could improve the answer scoring algorithm and (ii) to get higher benefits from the use of a named entity recognizer that was used last year in sub-optimal conditions. 2006 results were slightly better than last years, even though the question set included more definitions of type Que e X? (What is X?), with which the system had the worst results in previous participations.

Esfinge: a question answering system in the web using the web

Esfinge is a general domain Portuguese question answering system. It tries to take advantage of the great amount of information existent in the World Wide Web. Since Portuguese is one of the most used languages in the web and the web itself is a constantly growing source of updated information, this kind of techniques are quite interesting and promising.

What Happened to Esfinge in 2007

Esfinge is a general domain Portuguese question answering system which uses the information available on the Web as an additional resource when searching for answers. Other external resources and tools used are a broad coverage parser, a morphological analyser, a named entity recognizer and a Web-based database of word co-occurrences. In this fourth participation in CLEF, in addition to the new challenges posed by the organization (topics and anaphors in questions and the use of Wikipedia to search and support answers), we experimented with a multiple question and multiple answer approach in QA.

QolA: fostering collaboration within QA

In this paper we suggest a QA pilot task, dubbed QolA, whose joint rationale is allow for collaboration among systems, increase multilinguality and multicollection use, and investigate ways of dealing with different strengths and weaknesses of a population of QA systems. We claim that merging answers, weighting answers, choosing among contradictory answers or generating composite answers, and verifying and validating information, by posing related questions, should be part and parcel of the question answering process. The paper motivates these ideas and suggests a way to foster research in these areas by deploying QA systems as Web services.

SIGA, a system to manage information retrieval evaluations

This paper provides an overview of the current version of SIGA, a system that supports the organization of information retrieval (IR) evaluations. SIGA was recently used in Pagico, an evaluation contest where both automatic and human participants competed to find answers to 150 topics in the Portuguese Wikipedia, and we describe its new capabilities in this context as well as provide preliminary results from Pagico.

Studying Portuguese as Used: the AC/DC service

The AC/DC service has been giving access to Portuguese corpora through the Web since 1999. This paper describes the tasks related to processing and making the texts publicly available. It also provides an overview on the interface with which the users can query the corpora and finalizes pointing future directions.O AC/DC é um serviço que desde 1999 dá acesso a corpos emportuguês através da Internet. Neste artigo descrevemos sucintamente o processo pelo qual os textos são processados e tornados públicos e a interface através da qual se podem fazer as pesquisas. Concluímos lançando pontes para o desenvolvimento futuro deste serviço.