Pasar al contenido principal

The Multilingual Web of Data

RYC2019-028112-I

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal de Promoción del Talento y su Empleabilidad en I+D+i
Subprograma Subprograma Estatal de Incorporación
Convocatoria Ramón y Cajal
Año convocatoria 2019
Plan Estatal 2017-2020 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSIDAD DE ZARAGOZA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 7
Encontrada(s) 1 página(s)

RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Bilingual dictionary generation and enrichment via graph exploration

  • Goel, Shashwata
  • Gracia, Jorge
  • Forcada, Mikel L.
In recent years, we have witnessed a steady growth of linguistic information represented and exposed as linked data on the Web. Such linguistic linked data have stimulated the development and use of openly available linguistic knowledge graphs, as is the case with the Apertium RDF, a collection of interconnected bilingual dictionaries represented and accessible through Semantic Web standards. In this work, we explore techniques that exploit the graph nature of bilingual dictionaries to automatically infer new links (translations). We build upon a cycle density based method: partitioning the graph into biconnected components for a speed-up, and simplifying the pipeline through a careful structural analysis that reduces hyperparameter tuning requirements. We also analyse the shortcomings of traditional evaluation metrics used for translation inference and propose to complement them with new ones, both-word precision (BWP) and both-word recall (BWR), aimed at being more informative of algorithmic improvements. Over twenty-seven language pairs, our algorithm produces dictionaries about 70% the size of existing Apertium RDF dictionaries at a high BWP of 85% from scratch within a minute. Human evaluation shows that 78% of the additional translations generated for dictionary enrichment are correct as well. We further describe an interesting use-case: inferring synonyms within a single language, on which our initial human-based evaluation shows an average accuracy of 84%. We release our tool as free/open-source software which can not only be applied to RDF data and Apertium dictionaries, but is also easily usable for other formats and communities.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Bilingual dictionary generation and enrichment via graph exploration

  • Goel, S.
  • Gracia, J.
  • Forcada, M. L.
In recent years, we have witnessed a steady growth of linguistic information represented and exposed as linked data on the Web. Such linguistic linked data have stimulated the development and use of openly available linguistic knowledge graphs, as is the case with the Apertium RDF, a collection of interconnected bilingual dictionaries represented and accessible through Semantic Web standards. In this work, we explore techniques that exploit the graph nature of bilingual dictionaries to automatically infer new links (translations). We build upon a cycle density based method: partitioning the graph into biconnected components for a speed-up, and simplifying the pipeline through a careful structural analysis that reduces hyperparameter tuning requirements. We also analyse the shortcomings of traditional evaluation metrics used for translation inference and propose to complement them with new ones, both-word precision (BWP) and both-word recall (BWR), aimed at being more informative of algorithmic improvements. Over twenty-seven language pairs, our algorithm produces dictionaries about 70% the size of existing Apertium RDF dictionaries at a high BWP of 85% from scratch within a minute. Human evaluation shows that 78% of the additional translations generated for dictionary enrichment are correct as well. We further describe an interesting use-case: inferring synonyms within a single language, on which our initial human-based evaluation shows an average accuracy of 84%. We release our tool as free/open-source software which can not only be applied to RDF data and Apertium dictionaries, but is also easily usable for other formats and communities.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

When linguistics meets web technologies. Recent advances in modelling linguistic linked data

  • Khan, A. F.
  • Chiarcos, C.
  • Declerck, T.
  • Gifu, D.
  • González-Blanco García, E.
  • Gracia, J.
  • Ionov, M.
  • Labropoulou, P.
  • Mambrini, F.
  • McCrae, J. P.
  • Pagé-Perron, É.
  • Passarotti, M.
  • Ros Muñoz, S.
  • Truica, C. P.
This article provides a comprehensive and up-to-date survey of models and vocabularies for creating linguistic linked data (LLD) focusing on the latest developments in the area and both building upon and complementing previous works covering similar territory. The article begins with an overview of some recent trends which have had a significant impact on linked data models and vocabularies. Next, we give a general overview of existing vocabularies and models for different categories of LLD resource. After which we look at some of the latest developments in community standards and initiatives including descriptions of recent work on the OntoLex-Lemon model, a survey of recent initiatives in linguistic annotation and LLD, and a discussion of the LLD metadata vocabularies META-SHARE and lime. In the next part of the paper, we focus on the influence of projects on LLD models and vocabularies, starting with a general survey of relevant projects, before dedicating individual sections to a number of recent projects and their impact on LLD vocabularies and models. Finally, in the conclusion, we look ahead at some future challenges for LLD models and vocabularies. The appendix to the paper consists of a brief introduction to the OntoLex-Lemon model.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Results of the Translation Inference Across Dictionaries 2021 Shared Task

  • Gracia, Jorge
  • Kabashi, Besim
  • Kernerman, IIan
The objective of the Translation Inference Across Dictionaries (TIAD) shared task is to explore and compare methods and techniques that infer translations indirectly between language pairs, based on other bilingual/multilingual lexicographic resources. In this forth edition the participating systems were asked to generate new translations automatically among three languages - English, French, Portuguese - based on known indirect translations contained in the Apertium RDF graph. Such evaluation pairs have been the same during the three last TIAD editions. The main novelty this time has been the use of a larger graph as a basis to produce the translations, which is the Apertium RDF v2, and the introduction of improved evaluation metrics. The evaluation of the results was carried out by the organisers against manually compiled language pairs of K Dictionaries. For the first time in the TIAD series, some systems beat the proposed baselines. This paper gives an overall description of the shard task, the evaluation data and methodology, and the systems’ results.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

No clues good clues: out of context Lexical Relation Classification

  • Pitarch, Lucia
  • Bernad, Jordi
  • Dranca, Lacramioara
  • Bobed Lisbona, Carlos
  • Gracia, Jorge
The accurate prediction of lexical relations between words is a challenging task in Natural Language Processing (NLP). The most recent advances in this direction come with the use of pre-trained language models (PTLMs). A PTLM typically needs “well-formed” verbalized text to interact with it, either to fine-tune it or to exploit it. However, there are indications that commonly used PTLMs already encode enough linguistic knowledge to allow the use of minimal (or none) textual context for some linguistically motivated tasks, thus notably reducing human effort, the need for data pre-processing, and favoring techniques that are language neutral since do not rely on syntactic structures. In this work, we explore this idea for the tasks of lexical relation classification (LRC) and graded Lexical Entailment (LE). After fine-tuning PTLMs for LRC with different verbalizations, our evaluation results show that very simple prompts are competitive for LRC and significantly outperform graded LE SoTA. In order to gain a better insight into this phenomenon, we perform a number of quantitative statistical analyses on the results, as well as a qualitative visual exploration based on embedding projections.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Multilinguality and LLOD: A survey across linguistic description levels

  • Gromann, Dagmar
  • Apostol, Elena-Simona
  • Chiarcos, Christian
  • Cremaschi, Marco
  • Gracia, Jorge
  • Gkirtzou, Katerina
  • Liebeskind, Chaya
  • Mockiene, Liudmila
  • Rosner, Michael
  • Schuurman, Ineke
  • Sérasset, Gilles
  • Silvano, Purificação
  • Spahiu, Blerina
  • Truica, Ciprian-Octavian
  • Utka, Andrius
  • Valunaite Oleskeviciene, Giedre
Limited accessibility to language resources and technologies represents a challenge for the analysis, preservation, and documentation of natural languages other than English. Linguistic Linked (Open) Data (LLOD) holds the promise to ease the creation, linking, and reuse of multilingual linguistic data across distributed and heterogeneous resources. However, individual language resources and technologies accommodate or target different linguistic description levels, e.g., morphology, syntax, phonology, and pragmatics. In this comprehensive survey, the state-of-the-art of multilinguality and LLOD is being represented with a particular focus on linguistic description levels, identifying open challenges and gaps as well as proposing an ideal ecosystem for multilingual LLOD across description levels. This survey seeks to contribute an introductory text for newcomers to the field of multilingual LLOD, uncover gaps and challenges to be tackled by the LLOD community in reference to linguistic description levels, and present a solid basis for a future best practice of multilingual LLOD across description levels.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

SeqIA: A Python framework for extracting drought impacts from news archives

  • López-Otal, Miguel
  • Domínguez-Castro, Fernando
  • Latorre, Borja
  • Vela-Tambo, Javier
  • Gracia, Jorge
Drought is a hazard that causes great economic, ecological, and human loss. With an ever-growing risk of climate change, their frequency and magnitude are expected to increase. While there are many indices and metrics available for the analysis of droughts, assessing their impacts represents one of the best ways to understand their magnitude and extent. However, there are no systematic records outlining these impacts. To help in their ongoing creation, we present a software framework that leverages raw newspaper articles, identifies any drought-related ones, and automatically classifies them according to a set of socioeconomic impacts. The information is provided to the user in a structured format, including geographical coordinates and their date of reporting. Our approach employs state-of-the-art Transformer-based Natural Language Processing (NLP) techniques, which achieve great accuracy. We currently support newspaper articles in the Spanish language within Spain, but our framework can be expanded to other countries and languages.