Jing Zhang

@um.edu.mo

Department of Portuguese/Faculty of Arts and Humanity
University of Macau

5

Scopus Publications

Scopus Publications

  • AN EMPIRICAL STUDY ON THE VALIDITY OF THE FLUCTUATION HYPOTHESIS IN THE ACQUISITION OF PORTUGUESE ARTICLE BY CHINESE LEARNERS
    Jing Zhang

    University of Minho
    A aquisição do artigo é um processo no qual os aprendentes de L2 estabelecem gradualmente um valor semântico apropriado para o parâmetro do artigo. Segundo a Hipótese de Flutuação (Ionin, 2003), os aprendentes de uma L2 flutuam entre a marcação dos traços de definitude e de especificidade na escolha do artigo, o que é considerado uma propriedade temporária do sistema da sua interlíngua. Com uma longa exposição ao input da L2, os aprendentes vão estabelecendo o valor paramétrico adequado do artigo. O presente estudo visou testar, junto dos aprendentes chineses cuja L1 não possui este sistema linguístico, a validade da Hipótese de Flutuação. Os dados corroboraram a flutuação na escolha de artigos portugueses por este grupo de aprendentes de nível A2/B1 de proficiência em português, tendo apontado para o input de L2 e a Gramática Universal como fontes de conhecimento linguístico a que os aprendentes chineses recorrem para a aquisição do artigo em português. Esta pesquisa poderá contribuir como suporte teórico para o ensino do artigo em português a aprendentes chineses. 

  • Learning cognitive embedding using signed knowledge interaction graph
    Yujia Huo, Derek F. Wong, Lionel M. Ni, Lidia S. Chao, Jing Zhang, and Xin Zuo

    Elsevier BV

  • Comparative semantic study of the article system in portuguese and the determination marking mechanisms in chinese
    Jing Zhang

    University of Minho
    Um traço diferenciador da língua portuguesa e da língua chinesa é que a primeira possui o sistema de artigos e a segunda recorre a outros mecanismos para marcar o estado definido ou indefinido de sintagma nominal (SN). O presente trabalho compara as duas línguas, descrevendo a relação entre os dois sistemas de marcação de determinação e os tipos de SN classificados com base no modelo dos dois traços binários de Huebner (1983), segundo o qual o uso do artigo depende da função semântica de SN. Os resultados do estudo comparativo ajudam os alunos de língua materna chinesa a entender melhor como aplicar corretamente os artigos portugueses, estando cientes que os artigos portugueses codificam a definitude, não a especificidade.

  • HeTROPY: Explainable learning diagnostics via heterogeneous maximum-entropy and multi-spatial knowledge representation
    Yujia Huo, Derek F. Wong, Lionel M. Ni, Lidia S. Chao, and Jing Zhang

    Elsevier BV
    Abstract Autonomous learning diagnostics, where the students’ strengths and weaknesses are disclosed from their observed performance data, is a challenging task in e-learning systems. Current student knowledge models can alleviate some of the problems in learning (i.e. predicting student performance) but they neglect learning diagnostics, which is based on causal reasoning. To this end, we propose a novel heterogeneous attention interpreter with a maximum entropy regularizer on top of a student knowledge model to achieve explainable learning diagnostics. Our model segregates the impact of the homogeneous knowledge points, while promoting the heterogeneous relatives by maximizing their chance to contribute to the prediction. We also propose a multi-spatial knowledge representation that is readily generalizable to other data-driven educational tasks. Extensive experiments on real-world datasets reveal that the proposed method is able to enhance the model’s explanatory power, hence increases the trustworthiness towards learning diagnostics. It also brings notable improvement in accuracy in the student performance prediction task. The findings in this paper are adoptable to various types of e-learning systems to assist teachers to gain insights into student learning states and diagnose learning problems.

  • Knowledge modeling via contextualized representations for LSTM-based personalized exercise recommendation
    Yujia Huo, Derek F. Wong, Lionel M. Ni, Lidia S. Chao, and Jing Zhang

    Elsevier BV
    Abstract Intelligent education systems have enabled personalized learning (PL). In PL, students are presented with educational contents that are consistent with their personal knowledge states (KS), and the critical task is accurately estimating these states through data. Knowledge tracing (KT) infers KS (latent) through historical student interactions (observed) with the knowledge components (KCs). A wide variety of KT techniques have been developed, from Bayesian Knowledge Tracing (BKT) to Deep Knowledge Tracing (DKT). However, in most of these methods, the KCs are represented as stand-alone entities, and the effect of representing KCs using contexts such as learning-related factors has been under-investigated. Also, KT needs to generate personalized results to facilitate tasks such as exercise recommendation. In this paper, we propose two approaches that use a contextualized representation of KCs, one with a content-based approach and another with a Long Short Term Memory (LSTM) network plus a personalization mechanism. By performing extensive experiments on two real-world datasets, results show not only a tangible improvement in prediction accuracy in the KT task compared to existing methods, but also its effectiveness in improving the recommendation precision.