Mining biomedical information from scientific literature

The rapid evolution and proliferation of a world-wide computerized network, the Internet, resulted in an overwhelming and constantly growing amount of publicly available data and information, a fact that was also verified in biomedicine. However, the lack of structure of textual data inhibits its direct processing by computational solutions. Information extraction is the task of text mining that intends to automatically collect information from unstructured text data sources. The goal of the work described in this thesis was to build innovative solutions for biomedical information extraction from scientific literature, through the development of simple software artifacts for developers and biocurators, delivering more accurate, usable and faster results. We started by tackling named entity recognition - a crucial initial task - with the development of Gimli, a machine-learning-based solution that follows an incremental approach to optimize extracted linguistic characteristics for each concept type. Afterwards, Totum was built to harmonize concept names provided by heterogeneous systems, delivering a robust solution with improved performance results. Such approach takes advantage of heterogenous corpora to deliver cross-corpus harmonization that is not constrained to specific characteristics. Since previous solutions do not provide links to knowledge bases, Neji was built to streamline the development of complex and custom solutions for biomedical concept name recognition and normalization. This was achieved through a modular and flexible framework focused on speed and performance, integrating a large amount of processing modules optimized for the biomedical domain. To offer on-demand heterogenous biomedical concept identification, we developed BeCAS, a web application, service and widget. We also tackled relation mining by developing TrigNER, a machine-learning-based solution for biomedical event trigger recognition, which applies an automatic algorithm to obtain the best linguistic features and model parameters for each event type. Finally, in order to assist biocurators, Egas was developed to support rapid, interactive and real-time collaborative curation of biomedical documents, through manual and automatic in-line annotation of concepts and relations. Overall, the research work presented in this thesis contributed to a more accurate update of current biomedical knowledge bases, towards improved hypothesis generation and knowledge discovery.

Art-Map: concept of moving curatorial project and its practical realization in Aveiro

In this dissertation, I present the results of a project which aim was to find out and try an effective model of independent curatorial project executable in small and medium cities in Portugal. The concept of Moving Curatorial Project ARTMAP is a result of theoretical research and reflection about municipal exhibition spaces and possibility of presentation of the contemporary art in these spaces. To test if this curatorial project is realizable and if there are conditions to continue it, a first trial was implemented in Aveiro. A curated international exhibition, entitled “A Poética do Visual" occupied two municipal and two private gallery spaces and brought together 111 artists from 25 different countries. The art event was carried out in collaboration with the Municipality of Aveiro and the University of Aveiro, and involved several private cultural spaces in the city. This first experience showed that there are all conditions for the presentation of contemporary art in small and medium size locations in Portugal, and for this project to be replicated in other regions of the country.