A common semantic space for monolingual and cross-lingual meta-embeddings
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 spa...
| Autor: | |
|---|---|
| Tipo de recurso: | tesis de maestría |
| Fecha de publicación: | 2019 |
| País: | España |
| Institución: | Universidad del País Vasco |
| Repositorio: | Addi. Archivo Digital para la Docencia y la Investigación |
| OAI Identifier: | oai:addi.ehu.eus:10810/36183 |
| Acceso en línea: | http://hdl.handle.net/10810/36183 |
| Access Level: | acceso abierto |
| Palabra clave: | language analysis and processing monolingual meta-embeddings cross-lingual meta-embeddings |
| id |
ES_7db045d80df214271afa2b0b28a6a5b6 |
|---|---|
| oai_identifier_str |
oai:addi.ehu.eus:10810/36183 |
| network_acronym_str |
ES |
| network_name_str |
España |
| repository_id_str |
|
| spelling |
A common semantic space for monolingual and cross-lingual meta-embeddingsGarcía Ferrero, Ikerlanguage analysis and processingmonolingual meta-embeddingscross-lingual meta-embeddingsThis 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.Rigau Claramunt, Germán2019201920192019info:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10810/36183reponame:Addi. Archivo Digital para la Docencia y la Investigacióninstname:Universidad del País VascoInglésinfo:eu-repo/semantics/openAccesshttp://creativecommons.org/licenses/by-nc-sa/3.0/es/Atribución-NoComercial-CompartirIgual 3.0 Españaoai:addi.ehu.eus:10810/361832026-06-18T09:23:17Z |
| dc.title.none.fl_str_mv |
A common semantic space for monolingual and cross-lingual meta-embeddings |
| title |
A common semantic space for monolingual and cross-lingual meta-embeddings |
| spellingShingle |
A common semantic space for monolingual and cross-lingual meta-embeddings García Ferrero, Iker language analysis and processing monolingual meta-embeddings cross-lingual meta-embeddings |
| title_short |
A common semantic space for monolingual and cross-lingual meta-embeddings |
| title_full |
A common semantic space for monolingual and cross-lingual meta-embeddings |
| title_fullStr |
A common semantic space for monolingual and cross-lingual meta-embeddings |
| title_full_unstemmed |
A common semantic space for monolingual and cross-lingual meta-embeddings |
| title_sort |
A common semantic space for monolingual and cross-lingual meta-embeddings |
| dc.creator.none.fl_str_mv |
García Ferrero, Iker |
| author |
García Ferrero, Iker |
| author_facet |
García Ferrero, Iker |
| author_role |
author |
| dc.contributor.none.fl_str_mv |
Rigau Claramunt, Germán |
| dc.subject.none.fl_str_mv |
language analysis and processing monolingual meta-embeddings cross-lingual meta-embeddings |
| topic |
language analysis and processing monolingual meta-embeddings cross-lingual meta-embeddings |
| description |
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. |
| publishDate |
2019 |
| dc.date.none.fl_str_mv |
2019 2019 2019 2019 |
| dc.type.none.fl_str_mv |
info:eu-repo/semantics/masterThesis |
| format |
masterThesis |
| dc.identifier.none.fl_str_mv |
http://hdl.handle.net/10810/36183 |
| url |
http://hdl.handle.net/10810/36183 |
| dc.language.none.fl_str_mv |
Inglés |
| language_invalid_str_mv |
Inglés |
| dc.rights.none.fl_str_mv |
info:eu-repo/semantics/openAccess http://creativecommons.org/licenses/by-nc-sa/3.0/es/ Atribución-NoComercial-CompartirIgual 3.0 España |
| eu_rights_str_mv |
openAccess |
| rights_invalid_str_mv |
http://creativecommons.org/licenses/by-nc-sa/3.0/es/ Atribución-NoComercial-CompartirIgual 3.0 España |
| dc.format.none.fl_str_mv |
application/pdf |
| dc.source.none.fl_str_mv |
reponame:Addi. Archivo Digital para la Docencia y la Investigación instname:Universidad del País Vasco |
| instname_str |
Universidad del País Vasco |
| reponame_str |
Addi. Archivo Digital para la Docencia y la Investigación |
| collection |
Addi. Archivo Digital para la Docencia y la Investigación |
| repository.name.fl_str_mv |
|
| repository.mail.fl_str_mv |
|
| _version_ |
1869411682268217344 |
| score |
15,300724 |