Dimension reduction methods analysis in multilingual context in the educational field
In recent years, technological solutions base in context-aware and attention natural language processing have been a relevant research area. Undoubtedly, the last discoveries and advances on this subject have revolutionized the current landscape and have allowed to build high- performance models wit...
- Autores:
-
Sánchez Delgado, Juan Sebastián
- Tipo de recurso:
- Trabajo de grado de pregrado
- Fecha de publicación:
- 2023
- Institución:
- Universidad de los Andes
- Repositorio:
- Séneca: repositorio Uniandes
- Idioma:
- eng
- OAI Identifier:
- oai:repositorio.uniandes.edu.co:1992/74209
- Acceso en línea:
- https://hdl.handle.net/1992/74209
- Palabra clave:
- NLP
Reduction tecniques
PCA
TSNE
UMAP
Multilanguage
Ingeniería
- Rights
- embargoedAccess
- License
- Attribution-NonCommercial-NoDerivatives 4.0 International
| id |
UNIANDES2_648a6cef9112e1013e8e54dd26eb6f9b |
|---|---|
| oai_identifier_str |
oai:repositorio.uniandes.edu.co:1992/74209 |
| network_acronym_str |
UNIANDES2 |
| network_name_str |
Séneca: repositorio Uniandes |
| repository_id_str |
|
| dc.title.eng.fl_str_mv |
Dimension reduction methods analysis in multilingual context in the educational field |
| title |
Dimension reduction methods analysis in multilingual context in the educational field |
| spellingShingle |
Dimension reduction methods analysis in multilingual context in the educational field NLP Reduction tecniques PCA TSNE UMAP Multilanguage Ingeniería |
| title_short |
Dimension reduction methods analysis in multilingual context in the educational field |
| title_full |
Dimension reduction methods analysis in multilingual context in the educational field |
| title_fullStr |
Dimension reduction methods analysis in multilingual context in the educational field |
| title_full_unstemmed |
Dimension reduction methods analysis in multilingual context in the educational field |
| title_sort |
Dimension reduction methods analysis in multilingual context in the educational field |
| dc.creator.fl_str_mv |
Sánchez Delgado, Juan Sebastián |
| dc.contributor.advisor.none.fl_str_mv |
Manrique Piramanrique, Rubén Francisco |
| dc.contributor.author.none.fl_str_mv |
Sánchez Delgado, Juan Sebastián |
| dc.contributor.jury.none.fl_str_mv |
Manrique Piramanrique, Rubén Francisco |
| dc.subject.keyword.eng.fl_str_mv |
NLP |
| topic |
NLP Reduction tecniques PCA TSNE UMAP Multilanguage Ingeniería |
| dc.subject.keyword.none.fl_str_mv |
Reduction tecniques PCA TSNE UMAP Multilanguage |
| dc.subject.themes.spa.fl_str_mv |
Ingeniería |
| description |
In recent years, technological solutions base in context-aware and attention natural language processing have been a relevant research area. Undoubtedly, the last discoveries and advances on this subject have revolutionized the current landscape and have allowed to build high- performance models with several advanced applications such as conversational agents, translators, etc. The growing necessities of more complex models have caused and staggering increase not only in features size but also in the number of embedding dimensions. The present document pretends to analyze different dimensional reduction techniques applied to various courses translations versions in order to determine which approach lead to obtain the best clustering results. In contrast to previous works, the main focus will be to encounter which technique is the best suited for a small number of dimensions (between 2 and 4), in such a way that through visualization methods can be proved whether the current translations have an optimal level of similarity in terms of semantics and grammar to be considered valid. |
| publishDate |
2023 |
| dc.date.issued.none.fl_str_mv |
2023-12-11 |
| dc.date.accessioned.none.fl_str_mv |
2024-04-18T21:21:56Z |
| dc.date.accepted.none.fl_str_mv |
2024-04-18 |
| dc.date.available.none.fl_str_mv |
2025-03-31 |
| dc.type.none.fl_str_mv |
Trabajo de grado - Pregrado |
| dc.type.driver.none.fl_str_mv |
info:eu-repo/semantics/bachelorThesis |
| dc.type.version.none.fl_str_mv |
info:eu-repo/semantics/acceptedVersion |
| dc.type.coar.none.fl_str_mv |
http://purl.org/coar/resource_type/c_7a1f |
| dc.type.content.none.fl_str_mv |
Text |
| dc.type.redcol.none.fl_str_mv |
http://purl.org/redcol/resource_type/TP |
| format |
http://purl.org/coar/resource_type/c_7a1f |
| status_str |
acceptedVersion |
| dc.identifier.uri.none.fl_str_mv |
https://hdl.handle.net/1992/74209 |
| dc.identifier.instname.none.fl_str_mv |
instname:Universidad de los Andes |
| dc.identifier.reponame.none.fl_str_mv |
reponame:Repositorio Institucional Séneca |
| dc.identifier.repourl.none.fl_str_mv |
repourl:https://repositorio.uniandes.edu.co/ |
| url |
https://hdl.handle.net/1992/74209 |
| identifier_str_mv |
instname:Universidad de los Andes reponame:Repositorio Institucional Séneca repourl:https://repositorio.uniandes.edu.co/ |
| dc.language.iso.none.fl_str_mv |
eng |
| language |
eng |
| dc.relation.references.none.fl_str_mv |
1. A ́. Huertas-Garc ́ıa, A. Mart ́ın, J. Huertas-Tato, and D. Camacho, “Exploring di- mensionality reduction techniques in multilingual transformers,” Cognitive Com- putation, vol. 15, no. 2, pp. 590–612, 2023. 2. W. Jia, M. Sun, J. Lian, and S. Hou, “Feature dimensionality reduction: a review,” Complex & Intelligent Systems, vol. 8, no. 3, pp. 2663–2693, 2022. 3. C. Wang, L. Feng, L. Yang, T. Wu, and J. Zhang, “Dimensionality reduction by t-distribution adaptive manifold embedding,” Applied Intelligence, pp. 1–11, 2023. 4. M. S. Mauˇcec and G. Donaj, “Machine translation and the evaluation of its qual-ity,” Recent trends in computational intelligence, vol. 143, 2019. 5. D. Munkova, P. Ha ́jek, M. Munk, and J. Skalka, “Evaluation of machine transla- tion quality through the metrics of error rate and accuracy,” Procedia Computer Science, vol. 171, pp. 1327–1336, 01 2020. 6. T. Zhang, V. Kishore, F. Wu, K. Q. Weinberger, and Y. Artzi, “Bertscore: Evaluating text generation with BERT,” CoRR, vol. abs/1904.09675, 2019. 7. Y. Mao, L. Liu, Q. Zhu, X. Ren, and J. Han, “Facet-aware evaluation for extractive summarization,” arXiv preprint arXiv:1908.10383, 2019. 8. R. PL and G. KS, “Cognitive decline assessment using semantic linguistic content and transformer deep learning architecture,” International Journal of Language & Communication Disorders, vol. n/a, no. n/a. 9. A. R. Lahitani, A. E. Permanasari, and N. A. Setiawan, “Cosine similarity to determine similarity measure: Study case in online essay assessment,” in 2016 4th International Conference on Cyber and IT Service Management, pp. 1–6, 2016. 10. M. Iwasawa, D. Namekata, R. Sakamoto, T. Nakamura, Y. Kimura, K. Nitadori, L. Wang, M. Tsubouchi, J. Makino, Z. Liu, H. Fu, and G. Yang, “Implementation and performance of barnes-hut n-body algorithm on extreme-scale heterogeneous many-core architectures,” 2019. 11. R. Gove, L. Cadalzo, N. Leiby, J. M. Singer, and A. Zaitzeff, “New guidance for using t-sne: Alternative defaults, hyperparameter selection automation, and comparative evaluation,” Visual Informatics, vol. 6, no. 2, pp. 87–97, 2022. |
| dc.rights.en.fl_str_mv |
Attribution-NonCommercial-NoDerivatives 4.0 International |
| dc.rights.uri.none.fl_str_mv |
http://creativecommons.org/licenses/by-nc-nd/4.0/ |
| dc.rights.accessrights.none.fl_str_mv |
info:eu-repo/semantics/embargoedAccess |
| dc.rights.coar.none.fl_str_mv |
http://purl.org/coar/access_right/c_f1cf |
| rights_invalid_str_mv |
Attribution-NonCommercial-NoDerivatives 4.0 International http://creativecommons.org/licenses/by-nc-nd/4.0/ http://purl.org/coar/access_right/c_f1cf |
| eu_rights_str_mv |
embargoedAccess |
| dc.format.extent.none.fl_str_mv |
31 páginas |
| dc.format.mimetype.none.fl_str_mv |
application/pdf |
| dc.publisher.none.fl_str_mv |
Universidad de los Andes |
| dc.publisher.program.none.fl_str_mv |
Ingeniería de Sistemas y Computación |
| dc.publisher.faculty.none.fl_str_mv |
Facultad de Ingeniería |
| publisher.none.fl_str_mv |
Universidad de los Andes |
| institution |
Universidad de los Andes |
| bitstream.url.fl_str_mv |
https://repositorio.uniandes.edu.co/bitstreams/3d46d580-f64f-425f-8c0e-a8a9b499e1be/download https://repositorio.uniandes.edu.co/bitstreams/90f01e3d-abde-4771-a199-841637a6da0f/download https://repositorio.uniandes.edu.co/bitstreams/4777767f-ad21-419f-9b1b-7ace6c2e9f1a/download https://repositorio.uniandes.edu.co/bitstreams/9a1a0158-53a8-4078-aca9-9fd7fddfdbfe/download https://repositorio.uniandes.edu.co/bitstreams/4e8cbaec-763e-409b-a8ad-58a74a022b18/download https://repositorio.uniandes.edu.co/bitstreams/b71dd2e1-03bb-413f-98cd-b98a1792bd7f/download https://repositorio.uniandes.edu.co/bitstreams/4a1f7341-7911-4cc4-946c-82037f2599e3/download https://repositorio.uniandes.edu.co/bitstreams/21bba39a-a74e-4ec4-bccb-f2ba5ad1ff7e/download |
| bitstream.checksum.fl_str_mv |
558571fdab8672abc1782a0a5650551b acfd35de1091c638c65dfaf258ae2c46 ae9e573a68e7f92501b6913cc846c39f 4460e5956bc1d1639be9ae6146a50347 fc2c173767deebc829c69eb7e3077858 83caa7cbe0c95a8d1438c774bdff83ca ffd23679bf637477566b7fecf912dc7e c0ee98eca3e1aff27c7a28fd239bb836 |
| bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 MD5 MD5 MD5 MD5 |
| repository.name.fl_str_mv |
Repositorio institucional Séneca |
| repository.mail.fl_str_mv |
adminrepositorio@uniandes.edu.co |
| _version_ |
1812133898271850496 |
| spelling |
Manrique Piramanrique, Rubén Franciscovirtual::423-1Sánchez Delgado, Juan SebastiánManrique Piramanrique, Rubén Franciscovirtual::17917-12024-04-18T21:21:56Z2025-03-312023-12-112024-04-18https://hdl.handle.net/1992/74209instname:Universidad de los Andesreponame:Repositorio Institucional Sénecarepourl:https://repositorio.uniandes.edu.co/In recent years, technological solutions base in context-aware and attention natural language processing have been a relevant research area. Undoubtedly, the last discoveries and advances on this subject have revolutionized the current landscape and have allowed to build high- performance models with several advanced applications such as conversational agents, translators, etc. The growing necessities of more complex models have caused and staggering increase not only in features size but also in the number of embedding dimensions. The present document pretends to analyze different dimensional reduction techniques applied to various courses translations versions in order to determine which approach lead to obtain the best clustering results. In contrast to previous works, the main focus will be to encounter which technique is the best suited for a small number of dimensions (between 2 and 4), in such a way that through visualization methods can be proved whether the current translations have an optimal level of similarity in terms of semantics and grammar to be considered valid.Ingeniero de Sistemas y ComputaciónPregrado31 páginasapplication/pdfengUniversidad de los AndesIngeniería de Sistemas y ComputaciónFacultad de IngenieríaAttribution-NonCommercial-NoDerivatives 4.0 Internationalhttp://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/embargoedAccesshttp://purl.org/coar/access_right/c_f1cfDimension reduction methods analysis in multilingual context in the educational fieldTrabajo de grado - Pregradoinfo:eu-repo/semantics/bachelorThesisinfo:eu-repo/semantics/acceptedVersionhttp://purl.org/coar/resource_type/c_7a1fTexthttp://purl.org/redcol/resource_type/TPNLPReduction tecniquesPCATSNEUMAPMultilanguageIngeniería1. A ́. Huertas-Garc ́ıa, A. Mart ́ın, J. Huertas-Tato, and D. Camacho, “Exploring di- mensionality reduction techniques in multilingual transformers,” Cognitive Com- putation, vol. 15, no. 2, pp. 590–612, 2023.2. W. Jia, M. Sun, J. Lian, and S. Hou, “Feature dimensionality reduction: a review,” Complex & Intelligent Systems, vol. 8, no. 3, pp. 2663–2693, 2022.3. C. Wang, L. Feng, L. Yang, T. Wu, and J. Zhang, “Dimensionality reduction by t-distribution adaptive manifold embedding,” Applied Intelligence, pp. 1–11, 2023.4. M. S. Mauˇcec and G. Donaj, “Machine translation and the evaluation of its qual-ity,” Recent trends in computational intelligence, vol. 143, 2019.5. D. Munkova, P. Ha ́jek, M. Munk, and J. Skalka, “Evaluation of machine transla- tion quality through the metrics of error rate and accuracy,” Procedia Computer Science, vol. 171, pp. 1327–1336, 01 2020.6. T. Zhang, V. Kishore, F. Wu, K. Q. Weinberger, and Y. Artzi, “Bertscore: Evaluating text generation with BERT,” CoRR, vol. abs/1904.09675, 2019.7. Y. Mao, L. Liu, Q. Zhu, X. Ren, and J. Han, “Facet-aware evaluation for extractive summarization,” arXiv preprint arXiv:1908.10383, 2019.8. R. PL and G. KS, “Cognitive decline assessment using semantic linguistic content and transformer deep learning architecture,” International Journal of Language & Communication Disorders, vol. n/a, no. n/a.9. A. R. Lahitani, A. E. Permanasari, and N. A. Setiawan, “Cosine similarity to determine similarity measure: Study case in online essay assessment,” in 2016 4th International Conference on Cyber and IT Service Management, pp. 1–6, 2016.10. M. Iwasawa, D. Namekata, R. Sakamoto, T. Nakamura, Y. Kimura, K. Nitadori, L. Wang, M. Tsubouchi, J. Makino, Z. Liu, H. Fu, and G. Yang, “Implementation and performance of barnes-hut n-body algorithm on extreme-scale heterogeneous many-core architectures,” 2019.11. R. Gove, L. Cadalzo, N. Leiby, J. M. Singer, and A. Zaitzeff, “New guidance for using t-sne: Alternative defaults, hyperparameter selection automation, and comparative evaluation,” Visual Informatics, vol. 6, no. 2, pp. 87–97, 2022.202013577Publication9f6e12e0-098e-4548-ab81-75552e8385e7virtual::423-19f6e12e0-098e-4548-ab81-75552e8385e7virtual::423-19f6e12e0-098e-4548-ab81-75552e8385e7virtual::17917-19f6e12e0-098e-4548-ab81-75552e8385e7virtual::17917-1ORIGINALDimension_reduction_methods_analysis_in_multilingual_context_in_the_educational_field.pdfDimension_reduction_methods_analysis_in_multilingual_context_in_the_educational_field.pdfRestricción de acceso hasta 2025 para uso interno dentro del departamento para futuras publicaciones.application/pdf3900649https://repositorio.uniandes.edu.co/bitstreams/3d46d580-f64f-425f-8c0e-a8a9b499e1be/download558571fdab8672abc1782a0a5650551bMD51autorizacion tesis de grado.pdfautorizacion tesis de grado.pdfHIDEapplication/pdf648599https://repositorio.uniandes.edu.co/bitstreams/90f01e3d-abde-4771-a199-841637a6da0f/downloadacfd35de1091c638c65dfaf258ae2c46MD54LICENSElicense.txtlicense.txttext/plain; charset=utf-82535https://repositorio.uniandes.edu.co/bitstreams/4777767f-ad21-419f-9b1b-7ace6c2e9f1a/downloadae9e573a68e7f92501b6913cc846c39fMD52CC-LICENSElicense_rdflicense_rdfapplication/rdf+xml; charset=utf-8805https://repositorio.uniandes.edu.co/bitstreams/9a1a0158-53a8-4078-aca9-9fd7fddfdbfe/download4460e5956bc1d1639be9ae6146a50347MD55TEXTDimension_reduction_methods_analysis_in_multilingual_context_in_the_educational_field.pdf.txtDimension_reduction_methods_analysis_in_multilingual_context_in_the_educational_field.pdf.txtExtracted texttext/plain63713https://repositorio.uniandes.edu.co/bitstreams/4e8cbaec-763e-409b-a8ad-58a74a022b18/downloadfc2c173767deebc829c69eb7e3077858MD56autorizacion tesis de grado.pdf.txtautorizacion tesis de grado.pdf.txtExtracted texttext/plain1421https://repositorio.uniandes.edu.co/bitstreams/b71dd2e1-03bb-413f-98cd-b98a1792bd7f/download83caa7cbe0c95a8d1438c774bdff83caMD58THUMBNAILDimension_reduction_methods_analysis_in_multilingual_context_in_the_educational_field.pdf.jpgDimension_reduction_methods_analysis_in_multilingual_context_in_the_educational_field.pdf.jpgGenerated Thumbnailimage/jpeg9669https://repositorio.uniandes.edu.co/bitstreams/4a1f7341-7911-4cc4-946c-82037f2599e3/downloadffd23679bf637477566b7fecf912dc7eMD57autorizacion tesis de grado.pdf.jpgautorizacion tesis de grado.pdf.jpgGenerated Thumbnailimage/jpeg10979https://repositorio.uniandes.edu.co/bitstreams/21bba39a-a74e-4ec4-bccb-f2ba5ad1ff7e/downloadc0ee98eca3e1aff27c7a28fd239bb836MD591992/74209oai:repositorio.uniandes.edu.co:1992/742092024-04-19 03:03:25.625http://creativecommons.org/licenses/by-nc-nd/4.0/Attribution-NonCommercial-NoDerivatives 4.0 Internationalrestrictedhttps://repositorio.uniandes.edu.coRepositorio institucional Sénecaadminrepositorio@uniandes.edu.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 |