Persona:
Martínez Cantón, Clara Isabel

Cargando...
Foto de perfil
Dirección de correo electrónico
ORCID
0000-0003-0781-2418
Fecha de nacimiento
Proyectos de investigación
Unidades organizativas
Puesto de trabajo
Apellidos
Martínez Cantón
Nombre de pila
Clara Isabel
Nombre

Resultados de la búsqueda

Mostrando 1 - 5 de 5
  • Publicación
    The Diachronic Spanish Sonnet Corpus (DISCO): TEI and Linked Open Data Encoding, Data Distribution and Metrical Findings
    (2018) Ruiz Fabo, Pablo; Bermúdez Sabel, Helena; González-Blanco García, Elena; Navarro Colorado, Borja; Martínez Cantón, Clara Isabel
    This paper describes the DISCO corpus and how it complements available digital materials for poetry in Spanish in several respects: First, the author and period range. Second, metadata concerning the authors and their works expressed in TEI-RDFa, given the importance of interoperability between literary datasets and the advantages of Linked Open Data as a paradigm. Finally, example findings that can be obtained with our corpus are provided, regarding metrical patterns diachronically.
  • Publicación
    Poetry Lab (POSTER)
    (2018) González-Blanco García, Elena; Díez Platas, María Luisa; Ruiz Fabo, Pablo; Bermúdez Sabel, Helena; Ayciriex, Luciana; Ros Muñoz, Salvador; Martínez Cantón, Clara Isabel
    Main goals: a) Develop Tools for automatic poetry analysis, largely based on Natural Language Processing. b) Carry out the detection of literary phenomena relied on linguistic characteristics.
  • Publicación
    Poetry and Digital Humanities making interoperability possible in a divided world of digital poetry: POSTDATA project. (ABSTRACT)
    (2018) González-Blanco García, Elena; Ruiz Fabo, Pablo; Díez Platas, María Luisa; Bermúdez Sabel, Helena; Ayciriex, Luciana; Ros Muñoz, Salvador; Martínez Cantón, Clara Isabel; Caminero Herráez, Agustín Carlos
  • Publicación
    Procesamiento del lenguaje natural y fijación del texto. Experiencias en torno a la constitución de un corpus diacrónico de sonetos
    (Studia Aurea Monográfica, 2024-01-01) Bermúdez Sabel, Helena; Martínez Cantón, Clara Isabel; Ruiz Fabo, Pablo; Ministerio de Economía, Industria y Competitividad FFI2015-65093-P, Ministerio de Ciencia e Innovación PID2019-107928GB-I00
    Esta contribución surge en el contexto de desarrollo del corpus de sonetos DISCO (Diachronic Spanish Sonnet Corpus), un corpus de 4530 sonetos en español compuestos entre el siglo xvi y el xx por autores de diversas procedencias (Europa, Latinoamérica y Filipinas). Este recurso contiene las anotaciones de diferentes fenómenos de versificación que han sido obtenidas a partir de técnicas del procesamiento del lenguaje natural (PLN). En este artículo presentamos cómo los resultados de la anotación automática pueden ser utilizados para detectar problemas de transmisión textual. Uno de los objetivos de esta contribución es el de proporcionar claves sobre posibles flujos de trabajo que, ayudándose de herramientas de PLN, permitan detectar posibles errores textuales, centrando así los esfuerzos de revisión manual en pasajes concretos.
  • Publicación
    DISCOvering Spanish Sonnets: A Circular Reading Experience
    (DE GRUYTER, 2022-12-19) Bermúdez Sabel, Helena; Ruiz Fabo, Pablo; Martínez Cantón, Clara Isabel
    With DISCO, the DIachronic Spanish Sonnet COrpus, we collected 4085 sonnets, from the 15th to the 19th centuries, including canonical and lesser-studied authors from both Spain and Latin- America, with detailed author metadata, metrics, rhyme-scheme and enjambment annotations. The dataset is available on public repositories, offered in plain text and TEI, and enriched with RDFa, a linked-data format. The corpus was intended for research and teaching, as well as for non-specialist use. Some questions naturally emerge: How can we easily navigate this corpus and its rich metadata? How can we identify trends thanks to its annotations? How can users not proficient in XML query languages and linked data benefit from such a dataset? To address these issues, we have created DISCOver, a user-friendly web interface to explore the DISCO corpus. It was conceived as a means to help students, researchers, and readers overall, making the corpus accessible to a wider audience. The interface displays literary annotations on individual texts as well as quantitative data on user-defined subcorpora. In turn, from the aggregated data we can go back to the texts the data are based on. Thus, the interface helps us assess the features of individual texts in the context of quantitative data about larger parts of the corpus, and vice-versa. It also helps us nuance hypotheses based on aggregate data by consulting the texts they are derived from.