Atividade Profissional

  • 2016 Presente

    Professor Auxiliar Convidado

    Universidade da Beira Interior, Departamento de Informática

  • 2016 Presente

    Professor Convidado

    Instituto Politécnico da Guarda, Unidade Técnico-Científica de Informática

  • 2014 2016

    Investigador Científico

    TIMWE Investigação & Desenvolvimento

  • 2011 2014

    Gestor de Projectos e Engenheiro Informático

    Câmara Municipal da Covilhã, Serviço de Informática

  • 2007 2014

    Investigador Científico e Monitor

    Universidade da Beira Interior, Departamento de Informática, HULTIG - Centre For Human Language Tecnology and Bioinformatics

  • 2007 2014

    Formador

    AFTEBI - Associação para a Formação Tenológica e Profissional da Beira Interior

  • 2008 2013

    Investigador Científico

    MINES ParisTech - École des Mines de Paris, CRI - Centre de Recherche en Informatique

Graus Académicos

  • MCF 2017

    Qualificação de Maître de Conférences (MCF) em Informática

    Ministere de L'Education Nationale, de L'Enseignement Superieur et de la Recherche

  • PhD 2014

    PhD em Informática

    MINES Paristech

  • MSc2008

    Mestrado em Engenharia Informática, na Especialização de Computação e Sistemas Inteligentes

    Universidade da Beira Interior

  • BSc2007

    Licenciatura em Engenharia Informática, no Ramo de Sistemas de Informação (Pré-Bolonha, 5 anos)

    Universidade da Beira Interior

Projetos de Investigação

  • image

    HULTIG-C

    WEB

    Situação: Em Curso.

    O Hultig-C é um corpus que começou a ser desenvolvido em janeiro de 2017, e consiste em milhares de websites em diferentes idiomas e indexados com OpenWebSpider. O Hultig-C está a ser desenvolvido e mantido na UBI, pelo Hultig (Centro de Tecnologia da Linguagem Humana e Bioinformática) do Departamento de Informática. Este Corpus surge como resultado de um trabalho em curso que tem como objetivo dar suporte ao processamento automático da linguagem humana, alargando e melhorando gradualmente o Corpus, em todas as suas dimensões, de forma a providenciar um recurso de alto nível para a investigação em Linguística Computacional e para o desenvolvimento de aplicações e tecnologias da linguagem..

  • image

    AMBRO

    Programa: QREN

    Referência do projeto: 33779 QREN

    Situação: Concluído; Âmbito: Nacional.

    A TIMWE I&D propõe-se a desenvolver o projeto AMBRO, com vista à criação de um IPA que interage com todos os objetos que rodeiam o utilizador e que comuniquem através do protocolo IPv6. Desta forma é objetivo criar uma plataforma, associando um sistema que integra um ambiente persuasivo a um personal assistant, que permita tornar transparentes ao utilizador tarefas do dia-a-dia, como por exemplo, baseando-se na rotina matinal o AMBRO poderá, de forma autónoma, ligar a torradeira e a máquina do café, enquanto aquece a casa e informa o utilizador do estado do trânsito. Muitas destas tarefas são afetadas por variáveis externas, como localização, objetos disponíveis, permissões dentro da rede em que o utilizador se encontra, nível de treino da plataforma, etc. Com a evolução da tecnologia que nos rodeia, tentamos cada vez mais automatizar pequenas tarefas na vida do comum cidadão, para que o mesmo não tenha de se preocupar com determinadas tarefas com as quais se vai deparando diariamente.

    Resultados e Impacto: Criação de um ecossistema que suporte o funcionamento de IPAs (Inteligent Personal Assistants) e a sua integração em ambientes de computação ubíqua.

  • image

    VIP-ACCESS (Acesso Ubíquo à Web para Cegos)

    Programa: FCT

    Referência do projecto: PTDC/PLP/72142/2006

    Situação: Concluído; Âmbito: Internacional.

    Visually impaired people are info-excluded due to the overwhelming task they face to read information on the web. Indeed, unlike fully capacitated people, blind people can not read information by just scanning it quickly i.e. they can not read in the “diagonal”. As a consequence, they have to come through all sentences of web pages to understand if a document is interesting or not. This is obviously an overwhelming task which clearly excludes visually impaired people to quick access to information. Although a lot has been done for blind people to access information with braille screens, braille keyboards, braille PDAs andText-to-Speech interfaces, very little has been made to reduce the amount of information they have to deal with. For that purpose, we aim at proposing new human-computer interfaces that run on classical devices such as classical PCs, Pocket PCs or PDAs. As a consequence, blind people may have access to affordable technology. In particular, we aim at developing a wide range of technological solutions so that visually impaired people can take advantage of the new ubiquitous technologies that are fast growing in our every day lives.

    We aim at proposing new human-computer interfaces that run on classical devices such as classical PCs, Pocket PCs or PDAs. As a consequence, blind people may have access to affordable technology. In particular, we aim at developing a wide range of technological solutions so that visually impaired people can take advantage of the new ubiquitous technologies that are fast growing in our every day lives.

Filtrar por tipo:

Ordenar por ano:

Universal Mobile Information Retrieval

Machado, D.; Barbosa, T.; Pais, S.; Martins, B.; Dias, G.
Capítulo em Livro Universal Mobile Information Retrieval. Constantine Stephanidis. Universal Access in Human-Computer Interaction. Intelligent and Ubiquitous Interaction Environments. ed. Berlin, Heidelberg: Springer Berlin Heidelberg, 2009, v. 5615, p. 345-354. DOI: 10.1007/978-3-642-02710-9_38 ISSN/ISBN: 978-3-642-02709-3

Abstract

The shift in human computer interaction from desktop computing to mobile interaction highly influences the needs for new designed interfaces. In this paper, we address the issue of searching for information on mobile devices, an area also known as Mobile Information Retrieval. In particular, we propose to summarize as much as possible the information retrieved by any search engine to allow universal access to information.

Unsupervised and Language-Independent Method to Recognize Textual Entailment by Generality

Pais, S.; Dias, G.; Moraliyski, R.; Cordeiro, J.
Artigo em Conferência CONFERENCE COMPUTATIONAL LINGUISTICS IN BULGARIA 2014, Sofia. Proceedings of the First International Conference Computational Linguistics in Bulgaria. 2014.

Abstract

In this work we introduce a particular case of textual entailment (TE), namely Textual Entailment by Generality (TEG). In text, there are different kinds of entailment yielded from different types of implicative reasoning (lexical, syntactic, common sense based), but here we focus just on TEG, which can be defined as an entailment from a specific statement towards a relatively more general one. Therefore, we have T G → H whenever the premise T entails the hypothesis H, the hypothesis being more general than the premise. We propose an unsupervised and language-independent method to recognize TEGs, given a pair �T, H� in an entailment relation. We have evaluated our proposal through two experiments: (a) Test on T G −→ H English pairs, where we know that TEG holds; (b) Test on T → H Portuguese pairs, randomly selected with 60% of TEGs and 40% of TE without generality dependency (TEnG).

Recognize the Generality Relation between Sentences using Asymmetric Association Measures

Pais, S.; Dias, G.; Moraliyski, R.
Artigo em Conferência CONFERENCE COMPUTATIONAL LINGUISTICS IN BULGARIA 2014, Sofia. Proceedings of the First International Conference Computational Linguistics in Bulgaria. 2014.

Abstract

In this paper we focus on a particular case of entailment, namely entailment by generality. We argue that there exist various types of implication, a range of different levels of entailment reasoning, based on lexical, syntactic, logical and common sense clues, at different levels of difficulty. We introduce the paradigm of Textual Entailment (TE) by Generality, which can be defined as the entailment from a specific statement towards a relatively more general statement. In this context, the Text T entails the Hypothesis H, and at the same time H is more general than T. We propose an unsupervised and language-independent method to recognize TE by Generality given a case of T ext − Hypothesis or T − H where entailment relation holds.

Merged Agreement Algorithms for Domain Independent Sentiment Analysis

Lambov, D.; Pais, S.; Dias, G.
Artigo em Conferência 12TH CONFERENCE OF THE PACIFIC ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (PACLING 2011), 2011. Kuala Lumpur. Procedia Social and Behavioral Sciences. Selected Papers of the 12th Conference of the Pacific Association for Computational Linguistics. Elsevier Publishing, 2011.

Abstract

In this paper, we consider the problem of building models that have high sentiment classification accuracy across domains. For that purpose, we present and evaluate three new algorithms based on multi-view learning using both high-level and low-level views, which show improved results compared to the state-of-the-art SAR algorithm over cross-domain text subjectivity classification. Our experimental results present accuracy levels of 80% with two views, combining SVM classifiers over high-level features and unigrams compared to 77.1% for the SAR algorithm.

Textual Entailment by Generality

Dias, G.; Pais, S.; Wegrzyn-Wolska, K.; Mahl, R.
Artigo em Conferência 12TH CONFERENCE OF THE PACIFIC ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (PACLING 2011), 2011. Kuala Lumpur. Procedia Social and Behavioral Sciences. Selected Papers of the 12th Conference of the Pacific Association for Computational Linguistics. Elsevier Publishing, 2011.

Abstract

Textual Entailment consists in determining if an entailment relation exists between two texts. In this paper, we present an Informative Asymmetric Measure called the Asymmetric InfoSimba (AIS), which we combine with different asym-metric association measures to recognize the specific case of Textual Entailment by Generality. In particular, the AIS proposes an unsupervised, language-independent, threshold free solution. This new measure is tested against the first Recognizing Textual Entailment dataset for an exhaustive number of asymmetric association measures and shows that the combination of the AIS with the Braun-Blanket steadily improves results against competitive measures.

Recognizing Textual Entailment by Generality Using Informative Asymmetric Measures and Multiword Unit Identification to Summarize Ephemeral Clusters

Dias, G.; Pais, S.; Wegrzyn-Wolska, K.; Mahl, R.
Artigo em Conferência 2011 IEEE/WIC/ACM INTERNATIONAL JOINT CONFERENCES ON WEB INTELLIGENCE (WI) AND INTELLIGENT AGENT TECHNOLOGIES (IAT), 2011. Lyon, France. 2011 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology. IEEE, 2011, p. 284-287.

Abstract

In the context of Ephemeral Clustering of web Pages, it can be interesting to label each cluster with a small summary instead of just a label. Within this scope, we introduce the paradigm of Textual Entailment by Generality, which can be defined as the entailment from a specific web snippet towards a more general web snippet. The subjacent idea is to find the best web snippet, which summarizes and subsumes all the other web snippets within an ephemeral cluster. To reach this objective, we first propose a new informative asymmetric similarity measure called the Simplified Asymmetric InfoSimba(AISs), which can be combined with different asymmetric association measures. In particular, the AISs proposes an unsupervised language-independent solution to infer Textual Entailment by Generality and as such can help to encounter the web snippet with maximum semantic coverage. This new methodology is tested against the first Recognizing Textual Entailment data set (RTE-1)1 for an exhaustive number of asymmetric association measures with and without the identification of Multiword Units. The comparative experiments with existing state-of-the-art methodologies show promising results.

Hierarchical Soft Clustering and Automatic Text Summarization for Accessing the Web on Mobile Devices for Visually Impaired People

Dias, G.; Pais, S.; Cunha, F.; Costa, H.; Machado, D.; Barbosa, T.; Martins, B.
Artigo em Conferência 22ND INTERNATIONAL FLORIDA ARTIFICIAL INTELLIGENCE RESEARCH SOCIETY CONFERENCE, FLAIRS-22; SANIBEL ISLAND, FL; UNITED STATES, 2009. Florida. Proceedings of the 22nd International Florida Artificial Intelligence Research Society Conference. AAAI Publications, 2009, p. 231-236.

Abstract

In this paper, we propose a universal solution to web search and web browsing on handheld devices for visually impaired people. For this purpose, we propose (1) to automatically cluster web page results and (2) to summarize all the information in web pages so that speech-to-speech interaction is used efficiently to access information.

Universal Mobile Information Retrieval

Machado, D.; Barbosa, T.; Pais, S.; Martins, B.; Dias, G.
Artigo em Conferência 13TH INTERNATIONAL CONFERENCE ON HUMAN-COMPUTER INTERACTION HCI INTERNATIONAL, 2009. San Diego. Proceedings of the 13th International Conference on Human-Computer Interaction HCI International 2009.

Abstract

The shift in human computer interaction from desktop computing to mobile interaction highly influences the needs for new designed interfaces. In this paper, we address the issue of searching for information on mobile devices, an area also known as Mobile Information Retrieval. In particular, we propose to summarize as much as possible the information retrieved by any search engine to allow universal access to information.

Unsupervised Assistive and Adaptive Intelligent Agent in Smart Environment

Pais, S.; Casal, J.; Ponciano, R.; Lourenço, S.
Artigo em Revista World Academy of Science, Engineering and Technology, International Science Index, Computer and Information Engineering, v. 2, n. 1, p. 1067-1074, 2015. ISSN/ISBN: 1307-6892. Com arbitragem científica.

Abstract

The adaptation paradigm is a basic defining feature for pervasive computing systems. Adaptation systems must work efficiently in smart environment while providing suitable information relevant to the user system interaction. The key objective is to deduce the information needed information changes. Therefore, relying on fixed operational models would be inappropriate. This paper presents a study on developing a Intelligent Personal Assistant to assist the user in interacting with their Smart Environment. We propose a Unsupervised and Language-Independent Adaptation through Intelligent Speech Interface and a set of methods of Acquiring Knowledge, namely Semantic Similarity and Unsupervised Learning.

Using Accuracy Analysis to Find the Best Classifier for Intelligent Personal Assistants

Ponciano, R.; Pais, S.; Casal, J.
Artigo em Revista Procedia Computer Science, v. 52, n. 1, p. 310-317, 2015. ISSN/ISBN: 18770509. Com arbitragem científica.

Abstract

An Intelligent Personal Assistant (IPA) is an agent that has the purpose of helping the user with his daily tasks. This paper is focused on IPAs for Internet of Things (IoT) environments. In this sense, a good IPA has the capability of surveying his user behaviour and suggest tasks or make decisions with the intention of simplifying the user interaction with his surroundings. With this in mind, this paper focuses on studying the accuracy of various classifiers, with the objective of finding the one that suits better the needs of an IPA for IoT. The aim is to test each algorithm with a dataset of events, that relate to past behaviours of the user, and find if there is an opportunity to notify the user that he/she may want to take an action or create an automation based on the learned behaviour.

Merged Agreement Algorithms for Domain Independent Sentiment Analysis

Lambov, D.; Pais, S.; Dias, G.
Artigo em Revista Procedia - Social and Behavioral Sciences, Elsevier Publishing, v. 27, n. 1, p. 248-257, 2011. ISSN/ISBN: 18770428. Com arbitragem científica.

Abstract

In this paper, we consider the problem of building models that have high sentiment classification accuracy across domains. For that purpose, we present and evaluate three new algorithms based on multi-view learning using both high-level and low-level views, which show improved results compared to the state-of-the-art SAR algorithm over cross-domain text subjectivity classification. Our experimental results present accuracy levels of 80% with two views, combining SVM classifiers over high-level features and unigrams compared to 77.1% for the SAR algorithm.

Textual Entailment by Generality

Pais, S.; Dias, G.; Wegrzyn-Wolska, K.; Mahl, R.; Jouvelot, P.
Artigo em Revista Procedia - Social and Behavioral Sciences, Elsevier Publishing, v. 27, n. 1, p. 258-266, 2011. ISSN/ISBN: 18770428. Com arbitragem científica.

Abstract

Textual Entailment consists in determining if an entailment relation exists between two texts. In this paper, we present an Informative Asymmetric Measure called the Asymmetric InfoSimba (AIS), which we combine with different asym-metric association measures to recognize the specific case of Textual Entailment by Generality. In particular, the AIS proposes an unsupervised, language-independent, threshold free solution. This new measure is tested against the first Recognizing Textual Entailment dataset for an exhaustive number of asymmetric association measures and shows that the combination of the AIS with the Braun-Blanket steadily improves results against competitive measures.

Asymmetric Distributional Similarity Measures to Recognize Textual Entailment by Generality

Pais, S.
Dissertação PhD Dissertação para obtenção do grau de Ph.D. Mines Paristech, Paris.

Abstract

Textual Entailment aims at capturing major semantic inference needs across applications in Natural Language Processing. Since 2005, in the Textual Entailment recognition (RTE) task, systems are asked to automatically judge whether the meaning of a portion of text, the Text - T, entails the meaning of another text, the Hypothesis - H. This thesis we focus a particular case of entailment, entailment by generality. For us, there are various types of implication, we introduce the paradigm of Textual Entailment by Generality, which can be defined as the entailment from a specific sentence towards a more general sentence, in this context, the Text T entailment Hypothesis H, because H is more general than T. We propose methods unsupervised language-independent for Recognizing Textual Entailment by Generality, for this we present an Informative Asymmetric Measure called the Simplified Asymmetric InfoSimba, which we combine with different asymmetric association measures to recognizingthe specific case of Textual Entailment by Generality.This thesis, we introduce the new concept of implication, implications by generality, in consequence, the new concept of recognition implications by generality, a new direction of research in Natural Language Processing.

Classification of Opinionated Texts by Analogy.

Pais, S.
Dissertação MSc Dissertação para obtenção do grau de Mestre. Universidade da Beira Interior.

Atual

  • QS
    Qualidade de Software
    • Avisos

      Acesso a todo o conteúdo da Unidade Curricular: [WEB]

  • PDW
    Plataformas de Desenvolvimento Web
    • Avisos

      Acesso a todo o conteúdo da Unidade Curricular: [WEB]

  • PROG
    Programação
    • Avisos

      Acesso a todo o conteúdo da Unidade Curricular: [WEB]

  • ES
    Engenharia de Software
    • Avisos

      Sem informação até ao momento!!!

Orientação de trabalhos de conclusão de curso

  • 2017
    Paulo Pereira. Unsupervised and Language-Independent Methodology for Detection of Cyberbullying using Asymmetric Association Measures. Ano:2017 (Em curso). Engenharia Informática - Universidade da Beira Interior.
    Investigação, conceptualização e respetivo desenvolvimento experimental de uma metodologia não supervisionada e independente da língua para deteção de cyberbullying com recurso a medidas de associação assimétricas. A conceptualização e desenvolvimento desta metodologia visa testar métodos não supervisionados e independentes da língua, com a análise e estudo dos resultados vindos desses testes pretende-se contribuir com uma metodologia que para além de deteção de cyberbullying também tenha propriedades de prevenção.
  • 2017
    Fábio Barata. Indoor Location-Based Content. (Finalizado). Engenharia Informática - Universidade da Beira Interior.
    Investigação, conceptualização e respetivo desenvolvimento experimental de uma Plataforma Ubíqua, Escalável e Interoperativa para distribuição de conteúdos (independente da sua tipologia e tema) baseados na localização indoor de um utilizador, com recurso à tecnologia beacon. A conceptualização e desenvolvimento desta plataforma, em termos práticos assenta em três pilares essenciais: (i) Infraestrutura Cloud de Suporte; (ii) Interfaces Ubíquas para gestores da plataforma que têm a responsabilidade de distribuir conteúdos e (iii) Interfaces Ubíquas para os utilizadores alvo de conteúdos.
  • 2017
    Bruna Silva. Plataforma Ubíqua para Acompanhamento de Doentes Psiquiátricos em situação de Pós-Internamento. (Finalizado). Engenharia Informática - Universidade da Beira Interior
    Investigação, conceptualização e respetivo desenvolvimento experimental de uma Plataforma Ubíqua com foco no Acompanhamento e Auxilio de Doentes Psiquiátricos em situação de Pós-Internamento que pontualmente podem sofrer recaídas ou reversão da sua saúde mental. A conceptualização e desenvolvimento desta plataforma, em termos práticos assenta em três pilares essenciais: (i) Infraestrutura Cloud de Suporte; (ii) Interfaces Ubíquas para doentes psiquiátricos e (iii) Interfaces Ubíquas para profissionais de saúde.
  • 2017
    Joana Quadrado. Motor de Busca Móvel Educacional. (Finalizado). Engenharia Informática - Universidade da Beira Interior.
    Investigação, conceptualização e respetivo desenvolvimento experimental de um motor de busca móvel de imagens e vídeos, em que os utilizadores alvo são crianças que ainda não aprenderam a ler nem escrever. A conceptualização e desenvolvimento deste motor de busca, visa ser uma aplicação móvel educacional e de entretenimento controlado, de interação através do som.

Histórico

  • 2017 2016

    Aspetos Profissionais da Informática

    Bioinformática

    Engenharia de Software

    Qualidade de Software

    Plataformas de Desenvolvimento Web

    Programação de Dispositivos Móveis

  • 2015 2014

    Sistemas de Informção - Fundamentos

    Sistemas de Informção - Conceitos

  • 2015 2013

    Projecto de tecnologias e programação de sistemas de informação

    Planeamento e gestão de projectos de sistemas de informação

    Integração de sistemas de informação - tecnologias e níveis de Integração

    Integração de sistemas de informação - ferramentas

    Integração de sistemas de informação - conceitos

    Sistemas de Informação - concepção

    Inteligência Artificial

  • 2013 2012

    Sistemas de Informação - fundamentos

    Projeto

    Redes e Serviços Telemáticos

    Inteligência Artificial

  • 2012 2011

    Projecto

    Tecnologias da Internet e do Comércio Electrónico

    Redes e Serviços Telemáticos

    Projeto

    Redes e Serviços Telemáticos

    Tecnologias da Internet e do Comércio Electrónico

    Programação

    Tecnologias da Internet e do Comércio Electrónico

    Segurança da Internet e do Comércio Electrónico

  • 2011 2010

    Programação e Algoritmos

    Sistemas de Informação e Gestão

    Projecto II

    Programação

    Programação Orientada a Objectos

  • 2010 2009

    Projecto II

    Sistemas de Informação e Gestão

  • 2009 2008

    Programação

    Programação Orientada a Objectos

    Projecto I

  • 2008 2007

    Programação

    Projecto I

    Projecto II

    Redes e Serviços Telemáticos

    Sistemas de Informação e Gestão

  • 2007 2006

    Gestão de Projectos Informáticos