Data Science Institute (Conference Posters)

Permanent URI for this collection


Recent Submissions

  • Publication
    Sensemaking of complex sociotechnical systems: the case of governance dashboards
    (Association for Computing Machinery (ACM), 2018-05-30) Vornhagen, Heike; Davis, Brian; Zarrouk, Manel; Science Foundation Ireland; Horizon 2020
    This research project is concerned with developing a suitable visualization model to depict a complex socio-technical system such as a city. It focuses on governance dashboards as the main starting point as these aim to depict many aspects of a city and, it is argued, already reflect and shape a city in its totality. Governance dashboards however pose a number of challenges and may not be the most suitable visualisation for representing a city. It is proposed to create a visualisation model that would fully capture a city in its complexity whilst being cognisant of allowing users to engage with detail.
  • Publication
    Cardamom: Comparative deep models for minority and historical languages
    (Language Technologies for All (LT4All), 2019-12-05) McCrae, John Philip; Fransen, Theodorus
    This paper gives an overview of the Cardamom project, which aims to close the resource gap for minority and under-resourced languages by means of deep-learning-based natural language processing (NLP) and exploiting similarities of closely-related languages. The project further extends this idea to historical languages, which can be considered as closely related to their modern form, and as such aims to provide NLP through both space and time for languages that have been ignored by current approaches.
  • Publication
    Lexical sense alignment using weighted bipartite b-matching
    (NUI Galway, 2019-05-20) Ahmadi, Sina; Arcan, Mihael; McCrae, John; Thierry Declerck and John P. McCrae; Horizon 2020
    In this study, we present a similarity-based approach for lexical sense alignment in WordNet and Wiktionary with a focus on the polysemous items. Our approach relies on semantic textual similarity using features such as string distance metrics and word embeddings, and a graph matching algorithm. Transforming the alignment problem into a bipartite graph matching enables us to apply graph matching algorithms, in particular, weighted bipartite b-matching (WBbM).