Nuno Cardoso

Adding Geographic Scopes to Web Resources

Many web pages are rich in geographic information and primarily relevant to geographically limited communities. However, existing IR systems only recently began to offer local services and largely ignore geo-spatial information. This paper presents our work on automatically identifying the geographical scope of web documents, which provides the means to develop retrieval tools that take the geographical context into consideration. Our approach makes extensive use of an ontology of geographical concepts, and includes a system architecture for extracting geographic information from large collections of web documents. The proposed method involves recognising geographical references over the documents and assigning geographical scopes through a graph ranking algorithm. Initial evaluation results are encouraging, indicating the viability of this approach.

The University of Lisbon at GeoCLEF 2006

This paper details the participation of the XLDB Group from the University of Lisbon at the 2006 GeoCLEF task. We tested text mining methods that use an ontology to extract geographic references from text, assigning documents to encompassing geographic scopes. These scopes are used in document retrieval through a ranking function that combines BM25 text weighting with a similarity function for geographic scopes. We also tested a topic augmentation method, based on the geographic ontology, as an alternative to the scope-based approach.

Query expansion through geographical feature types

This paper introduces a new approach for expansion of queries with geographical context. The proposed strategy is based on a query parser that captures geonames and spatial relationships, and maps geographical features and feature types into concepts of a geographical ontology. Different strategies for query expansion, according to the geographical restrictions given by the user, are compared. The proposed method allows a more versatile and focused expansion towards the geographical information need of the user.

The XLDB group at GeoCLEF 2005

This paper describes our participation at GeoCLEF 2005. We detail the main software components of our Geo-IR system, its adaptation for GeoCLEF and the obtained results. The software architecture includes a geographic knowledge base, a text mining tool for geo-referencing documents, and a geo-ranking component. Results show that geo-ranking is heavily dependent on the information in the knowledge base and on the ranking algorithm involved.

Where in the Wikipedia is that answer? the XLDB at the GikiCLEF 2009 task

We developed a new semantic question analyser for a custom prototype assembled for participating in GikiCLEF 2009, which processes grounded concepts derived from terms, and uses information extracted from knowledge bases to derive answers. We also evaluated a newly developed named-entity recognition module, based in Conditional Random Fields, and a new world geoontology, derived from Wikipedia, which is used in the geographic reasoning process.

GikiP: evaluating geographical answers from wikipedia

This paper describes GikiP, a pilot task that took place in 2008 in CLEF. We present the motivation behind GikiP and the use of Wikipedia as the evaluation collection, detail the task and we list new ideas for its continuation.

Color fields computed in SU(3) lattice QCD for the static tetraquark system

The colour fields created by the static tetraquark system are computed in quenched SU(3) lattice QCD, in a 24^3 x 48 lattice at beta=6.2 corresponding to a lattice spacing a=0.07261(85) fm. We find that the tetraquark colour fields are well described by a double-Y, or butterfly, shaped flux tube. The two flux tube junction points are compatible with Fermat points minimizing the total flux tube length. We also compare the diquark-diantiquark central flux tube profile in the tetraquark with the quark-antiquark fundamental flux tube profile in the meson, and they match, thus showing that the tetraquark flux tubes are composed of fundamental flux tubes.

Using Geographic Signatures as Query and Document Scopes in Geographic IR

This paper reports the participation of the University of Lisbon at the 2007 GeoCLEF task. We adopted a novel approach for GIR, focused on handling geographic features and feature types on both queries and documents, generating signatures with multiple geographic concepts as a scope of interest. We experimented new query expansion and text mining strategies, relevance feedback approaches and ranking metrics.

A golden resource for named entity recognition in portuguese

This paper presents a collection of texts manually annotated with named entities in context, which was used for HAREM, the first evaluation contest for named entity recognizers for Portuguese. We discuss the options taken and the originality of our approach compared with previous evaluation initiatives in the area. We document the choice of categories, their quantitative weight in the overall collection and how we deal with vagueness and underspecification.

The XLDB group at CLEF 2004

This paper describes the participation of the XLDB Group in the CLEF monolingual ad hoc task for Portuguese. We present tumba!, a Portuguese search engine and describe its architecture and the underlying assumptions. We discuss the way we used tumba! in CLEF, providing details on our runs and our experiments with ranking algorithms.