Medical information extraction in European Portuguese

The electronic storage of medical patient data is becoming a daily experience in most of the practices and hospitals worldwide. However, much of the data available is in free-form text, a convenient way of expressing concepts and events, but especially challenging if one wants to perform automatic searches, summarization or statistical analysis. Information Extraction can relieve some of these problems by offering a semantically informed interpretation and abstraction of the texts. MedInX, the Medical Information eXtraction system presented in this document, is the first information extraction system developed to process textual clinical discharge records written in Portuguese. The main goal of the system is to improve access to the information locked up in unstructured text, and, consequently, the efficiency of the health care process, by allowing faster and reliable access to quality information on health, for both patient and health professionals. MedInX components are based on Natural Language Processing principles, and provide several mechanisms to read, process and utilize external resources, such as terminologies and ontologies, in the process of automatic mapping of free text reports onto a structured representation. However, the flexible and scalable architecture of the system, also allowed its application to the task of Named Entity Recognition on a shared evaluation contest focused on Portuguese general domain free-form texts. The evaluation of the system on a set of authentic hospital discharge letters indicates that the system performs with 95% F-measure, on the task of entity recognition, and 95% precision on the task of relation extraction. Example applications, demonstrating the use of MedInX capabilities in real applications in the hospital setting, are also presented in this document. These applications were designed to answer common clinical problems related with the automatic coding of diagnoses and other health-related conditions described in the documents, according to the international classification systems ICD-9-CM and ICF. The automatic review of the content and completeness of the documents is an example of another developed application, denominated MedInX Clinical Audit system.

English picturebook illustrations and language development in early years education

Este estudo investiga a influência da interação imagem-texto de três álbuns ilustrados de língua inglesa no desenvolvimento do repertório linguístico de crianças pré-leitoras. Numa metodologia de estudo de caso, adotando uma abordagem qualitativa e socio construtivista num contexto real de educação pré-escolar, três grupos de crianças portuguesas foram filmados ao longo de várias sessões de leitura repetida em voz alta e em inglês, e de sessões de recontos trabalhados em pequenos grupos. Após a transcrição das gravações, o corpus resultante foi analisado com base numa teoria fundamentada de compreensão literária e em escalas de leitura emergente. Os resultados mostraram que as crianças adotaram uma postura fortemente analítica face aos álbuns, direcionando as suas respostas para as ilustrações e usando-as como apoio na construção de significados. Os resultados mostraram também que cada interanimação visual e verbal ofereceu diversas oportunidades para o uso das línguas em presença, o português e o inglês, tendo o formato e a estrutura inerentes a cada álbum contribuído de forma muito relevante para as respostas das crianças. Contudo, os álbuns com uma dinâmica imagem-texto mais complexa proporcionaram um maior envolvimento das crianças, provocando mais discussão em torno das ilustrações e criando mais oportunidades para mediação do uso da segunda língua. Os resultados revelaram ainda a importância da interação durante as leituras repetidas, na compreensão e na análise narrativa, num processo de desenvolvimento da linguagem. Com base nestes resultados, apontam-se conclusões, com implicações para os contextos educativos, quer ao nível da língua materna, quer ao nível da segunda língua, nomeadamente em relação: à seleção de álbuns e à valorização das ilustrações e ainda à importância de leituras repetidas em voz alta e à discussão realizada pelas crianças.

Psicomotricidade e resiliência em crianças brasileiras e portuguesas: um estudo comparativo para a melhoria no ensino-aprendizagem

O presente trabalho tem como objetivo avaliar a eficácia da aplicação de um programa que visa o desenvolvimento psicomotor e a resiliência em crianças brasileiras (de classes desfavorecidas) e portuguesas (meio rural). Foram implementados 3 estudos: no primeiro, exploratório, foi realizado um programa de intervenção na área da resiliência com 76 crianças portuguesas e 151 crianças brasileiras com idades entre os 3 e os 5 anos de idade, divididas em Grupo Experimental (submetido ao programa de intervenção Strong Start Pré- K, da Universidade do Oregon, adaptado às realidades portuguesa e brasileira) e Grupo Controlo (sem intervenção),avaliadas pelo questionário WeBeST (Well-Being Screening Tool) antes e depois da intervenção. O segundo estudo realizado numa ONG brasileira pretende avaliar o efeito da psicomotricidade e foi dividido em duas fases: fase A, que contou 32 crianças brasileiras de 5 anos de idade, que frequentam a Instituição em período integral e 28 crianças que frequentam em meio período. Na fase B foi aplicado um programa de intervenção (nas 28 crianças da fase A) para se avaliar o efeito dessa intervenção. O instrumento de avaliação utilizado na área foi o Inventário Portage, adaptado e operacionalizado para a população brasileira, que consta de 580 itens divididos em seis áreas (Autocuidados, Cognição, Desenvolvimento Motor, Estimulação Infantil, Linguagem e Socialização). O terceiro estudo avaliou apenas nas crianças de 5 anos, os efeitos da resiliência e psicomotricidade nas 28 crianças brasileiras da fase A e B (do estudo 2) e em 35 crianças portuguesas (do estudo 1). Pudemos constatar no primeiro estudo que quer as crianças portuguesas, quer as brasileiras submetidas ao programa de intervenção na área da resiliência obtiveram melhores resultados que as não submetidas ao mesmo programa. Quanto aos resultados obtidos na fase A do segundo estudo na área da psicomotricidade, as crianças da ONG brasileira, que frequentavam o período integral obtiveram melhores resultados que as não requentavam. Já na fase B, estas ao serem submetidas ao programa de intervenção específico, obtiveram resultados significativos, o que sugere que o Programa de intervenção foi eficaz, quer para as crianças que o tiveram anteriormente no período integral, quer para as que foram submetidas a ele na fase posterior. No último estudo, as crianças brasileiras apresentaram melhores resultados que as portuguesas. Não foi possível fazer um estudo comparativo entre Portugal e Brasil, relativamente à área da psicomotricidade, visto que na realidade portuguesa, desde os anos 70 é obrigatória na educação pré-escolar a psicomotricidade. São referidas algumas implicações psicopedagógicas resultantes deste tipo de intervenção, perspetivando a melhoria da qualidade de ensino e aprendizagem e o desenvolvimento de personalidades resilientes das crianças.

Robust handling of out-of-vocabulary words in deep language processing

Tese de doutoramento, Informática (Ciências da Computação), Universidade de Lisboa, Faculdade de Ciências, 2014

English as a lingua Franca : bridging the gap between theory and practice in english language teaching

Tese de doutoramento, Linguística (Linguística Aplicada), Universidade de Lisboa, Faculdade de Letras, 2015

Pronoun-dropping or zero anaphora in translation from german into portuguese

In this article I will analyse anaphoric references in German texts and their transaltion into Portuguese. I will take as main corpus Heinrich Böll's novel Haus ohne Hüter and its translation into Portuguese by Jorge Rosa with the title Casa Indefesa. I will concentrate on the use of personal pronouns and possessives in references to both people and objects in source text and target text and I will present patterns of symmetries and asymmetries. I will claim that asymmetries in the translation of such anaphoric references can be accounted for mainly by differences in the pronominal systems and verbal systems of both languages and by differences in the way each language marks theme/topic continuity/discontinuity in discourse. Issues related to style and the translation of anaphors will also be addressed. I will finally raise some questions related to ambiguous references which can not be solved within the scope of syntax or semantics, thus requiring pragmatic interpretation based on cultural knowledge/world knowledge.

A rule-based grapheme-to-phone converter for TTS systems in european portuguese

In this paper, a linguistically rule-based grapheme-to-phone (G2P) transcription algorithm is described for European Portuguese. A complete set of phonological and phonetic transcription rules regarding the European Portuguese standard variety is presented. This algorithm was implemented and tested by using online newspaper articles. The obtained experimental results gave rise to 98.80% of accuracy rate. Future developments in order to increase this value are foreseen. Our purpose with this work is to develop a module/ tool that can improve synthetic speech naturalness in European Portuguese. Other applications of this system can be expected like language teaching/learning. These results, together with our perspectives of future improvements, have proved the dramatic importance of linguistic knowledge on the development of Text-to-Speech systems (TTS).

Self-initiation expatriation: A focus on Italian and Portuguese students

The purpose of this work project is to analyze the phenomenon of self-initiated expatriation (SIE) through its link to the Protean Career and Career Capital theories, focusing in particular on Italian and Portuguese students attending a Master in the business area. The main research questions are to understand the reasons driving the intention to expatriate, after the conclusion of the academic path, using three main categories (Adventure Motivation, Work Characteristic Motivation and instrumental Motivation) and the intention to repatriate. A sample of Italian and Portuguese students was obtained. Italians show a higher intention to expatriate relative to Portuguese; nevertheless, no other significant differences were found among the two populations, because of the similar cultural background and economic situation. Additionally, several heterogeneities were observed considering other clusters defined by Gender, Teaching Language of the Master and Past International Experiences, across the two nationalities. Furthermore, possible future researches and practical implications were discussed.

Internationalization strategy of reliance to Brazil

This Work Project was focused, firstly, in an internal analysis to assess the possible competitive advantage sources of the firm and to identify the key weakness that the firm should improve before advancing with the internationalization strategy. Completed the analysis was possible to verify that the source of sustainable competitive advantage of Relance is the use of specific raw materials and that its biggest weaknesses are the lack of capacity and the excessive dependence on key employees. Overall, it was possible to conclude that the firm is in position of competing in the international markets. Secondly, due to its crucial importance, the country selection was made with a deep objective analysis, resulting with the selection of Brazil as the country with the highest market potential. Regarding the strategy to actually enter in Brazil’s market, after the study of 12 modes of entry it was possible to conclude that there is no ideal mode. However, the study performed allowed to undertake the conclusion that in order to obtain long-term optimization on the process, the adaptation, to the firm´s situation, of the Uppsala model progressive stages is the ideal. At the course of this Work Project it was inferred that the critical success factors are the choice of the distributor and the promotion of Relance as a premium brand.

Back to the margins in search of the core: "Foreign Land"'s geography of exclusion

The crisis of the national project in the early 1990s, caused by a short-lived but disastrous government, led Brazilian art cinema, for the first time, to look at itself as periphery and re-approach the old colonial center, Portugal. Terra estrangeira/Foreign Land (Walter Salles & Daniela Thomas, Brazil/Portugal, 1995), a film about Brazilian exiles in Portugal, is the best illustration of this perspective shift which provides a new sense of Brazil’s scale and position within a global context. Shot mainly on location in São Paulo, Lisbon and Cape Verde, it promotes the encounter of Lusophone peoples who find a common ground in their marginal situation. Rather than as a former empire, Portugal is defined by its situation at the edge of Europe and by beliefs such as Sebastianism, whose origins go back to the time when the country was dominated by Spain. As a result, notions of “core” or “center” are devolved to the realm of myth. The film’s carefully crafted dialogue combines Brazilian, Portuguese and Creole linguistic peculiarities into a common dialect of exclusion, while language puns trigger visual rhymes which refer back to the Cinema Novo (the Brazilian New Wave) repertoire and restage the imaginary of the discovery turned into unfulfilled utopia. The main characters also acquire historical resonances, as they are depicted as descendants of Iberian conquistadors turned into smugglers of precious stones in the present. Their activities define a circuit of international exchange which resonates with that of globalized cinema, a realm in which Foreign Land, made up of citations and homage to other cinemas, tries to retrieve a sense of belonging.

Back to the margins in search of the core: foreign land's geography of exclusion

The crisis of the national project in the early 1990s, caused by a short-lived but disastrous government, led Brazilian art cinema, for the first time, to look at itself as periphery and re-approach the old colonial centre, Portugal. Terra estrangeira/Foreign Land (Walter Salles & Daniela Thomas, Brazil/Portugal, 1995), a film about Brazilian exiles in Portugal, is the best illustration of this perspective shift aimed at providing a new sense of Brazil’s scale and position within a global context. Shot mainly on location in São Paulo, Lisbon and Cape Verde, it promotes the encounter of Lusophone peoples who find a common ground in their marginal situation. Even Portugal is defined by its location at the edge of Europe and by beliefs such as Sebastianism, whose origins go back to the time when the country was dominated by Spain. As a result, notions of ‘core’ or ‘centre’ are devolved to the realm of myth. The film’s carefully crafted dialogues combine Brazilian, Portuguese and Creole linguistic peculiarities into a common dialect of exclusion, while language puns trigger visual rhymes which refer back to the Cinema Novo (the Brazilian New Wave) repertoire and restage the imaginary of the discovery turned into unfulfilled utopia. The main characters also acquire historical resonances, as they are depicted as descendants of Iberian conquistadors turned into smugglers of precious stones in the present. Their activities define a circuit of international exchange which resonates with that of globalized cinema, a realm in which Foreign Land, made up of citations and homage to other cinemas, tries to retrieve a sense of belonging.

On the typological economy of syntactic transfer: word order and relative clause high/low attachment preference in L3 Brazilian Portuguese

One central question in the formal linguistic study of adult multilingual morphosyntax (i.e., L3/Ln acquisition) involves determining the role(s) the L1 and/or the L2 play(s) at the L3 initial state (e.g., Bardel & Falk, Second Language Research 23: 459–484, 2007; Falk & Bardel, Second Language Research: forthcoming; Flynn et al., The International Journal of Multilingualism 8: 3–16, 2004; Rothman, Second Language Research: forthcoming; Rothman & Cabrelli, On the initial state of L3 (Ln) acquisition: Selective or absolute transfer?: 2007; Rothman & Cabrelli Amaro, Second Language Research 26: 219–289, 2010). The present article adds to this general program, testing Rothman's (Second Language Research: forthcoming) model for L3 initial state transfer, which when relevant in light of specific language pairings, maintains that typological proximity between the languages is the most deterministic variable determining the selection of syntactic transfer. Herein, I present empirical evidence from the later part of the beginning stages of L3 Brazilian Portuguese (BP) by native speakers of English and Spanish, who have attained an advanced level of proficiency in either English or Spanish as an L2. Examining the related domains of syntactic word order and relative clause attachment preference in L3 BP, the data clearly indicate that Spanish is transferred for both experimental groups irrespective of whether it was the L1 or L2. These results are expected by Rothman's (Second Language Research: forthcoming) model, but not necessarily predicted by other current hypotheses of multilingual syntactic transfer; the implications of this are discussed.