Fiche du document
2020
- 20.500.13089/1djh
Ce document est lié à :
https://hdl.handle.net/20.500.13089/1cho
Ce document est lié à :
https://doi.org/10.4000/books.aaccademia
Ce document est lié à :
info:eu-repo/semantics/altIdentifier/isbn/979-12-80136-32-9
info:eu-repo/semantics/openAccess , https://creativecommons.org/licenses/by-nc-nd/4.0/
Sujets proches
Parliamentary government Representation Self-government Political representation Documents Documents, Legal Documents Public documents Official publications Government documents Produce Agricultural products Agricultural commodities Pattern Model Documents Documents Indentures Date Competition (Economics) Economic competition Competitiveness (Economics) Knowledge, Classification of Documents Charters--Law and legislation Documents Manuscript repositories Manuscript depositories Manuscripts--Repositories Manuscripts--Depositories Western architecture (Western countries) Building design Construction Buildings--Design and construction Architecture, Western (Western countries)Citer ce document
Riccardo Massidda, « rmassidda @ DaDoEval: Document Dating Using Sentence Embeddings at EVALITA 2020 », Accademia University Press
Partage / Export
Résumé
This report describes an approach to solve the DaDoEval document dating subtasks for the EVALITA 2020 competition. The dating problem is tackled as a classification problem, where the significant length of the documents in the provided dataset is addressed by using sentence embeddings in a hierarchical architecture. Three different pre-trained models to generate sentence embeddings have been evaluated and compared: USE, LaBSE and SBERT. Other than sentence embeddings the classifier exploits a bag-of-entities representation of the document, generated using a pre-trained named entity recognizer. The final model is able to simultaneously produce the required date for each subtask.
