dc.contributor.advisor | Rigau Claramunt, Germán | |
dc.contributor.author | García Ferrero, Iker | |
dc.date.accessioned | 2019-10-30T09:25:14Z | |
dc.date.available | 2019-10-30T09:25:14Z | |
dc.date.issued | 2019-10-29 | |
dc.date.submitted | 2019-09-23 | |
dc.identifier.uri | http://hdl.handle.net/10810/36183 | |
dc.description.abstract | This master’s thesis presents a new technique for creating monolingual and cross-lingual meta-embeddings. Our method integrates multiple word embeddings created from complementary techniques, textual sources, knowledge bases and languages. Existing word vectors are projected to a common semantic space using linear transformations and averaging. With our method the resulting meta-embeddings maintain the dimensionality of the original embeddings without losing information while dealing with the out-of-vocabulary (OOV) problem. Furthermore, empirical evaluation demonstrates the effectiveness of our technique with respect to previous work on various intrinsic and extrinsic multilingual evaluations. | es_ES |
dc.language.iso | eng | es_ES |
dc.rights | info:eu-repo/semantics/openAccess | es_ES |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-sa/3.0/es/ | * |
dc.subject | language analysis and processing | |
dc.subject | monolingual meta-embeddings | |
dc.subject | cross-lingual meta-embeddings | |
dc.title | A common semantic space for monolingual and cross-lingual meta-embeddings | es_ES |
dc.type | info:eu-repo/semantics/masterThesis | es_ES |
dc.rights.holder | Atribución-NoComercial-CompartirIgual 3.0 España | * |
dc.departamentoes | Lenguajes y sistemas informáticos | es_ES |
dc.departamentoeu | Hizkuntza eta sistema informatikoak | es_ES |