Incrustaciones contextualizadas de palabras con ELMO

Segura González, David Stiven

Incrustaciones contextualizadas de palabras con ELMO

dc.contributor.advisor	Másmela Caita, Luis Alejandro
dc.contributor.author	Segura González, David Stiven
dc.contributor.orcid	Másmela Caita, Luis Alejandro [0000-0003-3882-4980]
dc.contributor.other	García Barreto, Germán Alberto (Catalogador)
dc.date.accessioned	2025-05-22T22:09:42Z
dc.date.available	2025-05-22T22:09:42Z
dc.date.created	2024-12-12
dc.description	El procesamiento del lenguaje natural (NLP, por sus siglas en inglés) es un campo esencial y en constante evolución dentro del aprendizaje automático, con aplicaciones como la traducción automática, chatbots, análisis de sentimientos y detección de plagio. Los modelos de aprendizaje automático para NLP buscan representaciones eficientes de palabras mediante distintas codificaciones, destacando las incrustaciones de palabras, que ofrecen una representación vectorial simplificada. Sin embargo, estos modelos tradicionales suelen omitir el contexto de las palabras. En este sentido, surge ELMo (Embeddings from Language Models), un modelo que considera el contexto para generar representaciones vectoriales dinámicas. ELMo emplea un modelo bidireccional de lenguaje (biLM), basado en redes neuronales como CNN, LSTM, y High-Way Network, permitiendo capturar el contexto y resolver problemas de polisemia. Presentado en 2018 por investigadores del Instituto Allen NLP y la Universidad de Washington, ELMo representa un avance significativo en el campo.
dc.description.abstract	Natural language processing (NLP) is an essential and evolving field within machine learning, with applications such as machine translation, chatbots, sentiment analysis and plagiarism detection. Machine learning models for NLP seek efficient representations of words using different encodings, most notably word embeddings, which provide a simplified vector representation. However, these traditional models often omit the context of words. In this sense, ELMo (Embeddings from Language Models), a model that considers the context to generate dynamic vector representations, has emerged. ELMo employs a bidirectional language model (biLM), based on neural networks such as CNN , LSTM , and High-Way Network , allowing to capture context and solve polysemy problems. Introduced in 2018 by researchers at the Allen NLP Institute and the University of Washington, ELMo represents a significant advance in the field.
dc.format.mimetype	pdf
dc.identifier.uri	http://hdl.handle.net/11349/95652
dc.language.iso	spa
dc.publisher	Universidad Distrital Francisco José de Caldas
dc.relation.references	Yoshua Bengio, Réjean Ducharme, Pascal Vincent, and Christian Janvin. A neural probabilistic language model. J. Mach. Learn. Res., 3(null):1137–1155, mar 2003.
dc.relation.references	Sepp Hochreiter and Jürgen Schmidhuber. Long short-term memory. Neural computation, 9:1735– 80, 12 1997.
dc.relation.references	Daniel Jurafsky and James H. Martin. Speech and Language Processing. Stanford University Press, 2024.
dc.relation.references	Yoon Kim, Yacine Jernite, David Sontag, and Alexander M. Rush. Character-aware neural language models, 2015
dc.relation.references	Tomás Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. Efficient estimation of word representations in vector space. In Yoshua Bengio and Yann LeCun, editors, 1st International Conference on Learning Representations, ICLR 2013, Scottsdale, Arizona, USA, May 2-4, 2013, Workshop Track Proceedings, 2013.
dc.relation.references	Jeffrey Pennington, Richard Socher, and Christopher Manning. GloVe: Global vectors for word representation. In Alessandro Moschitti, Bo Pang, and Walter Daelemans, editors, Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1532–1543, Doha, Qatar, October 2014. Association for Computational Linguistics.
dc.relation.references	Matthew E. Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, and Luke Zettlemoyer. Deep contextualized word representations. In Marilyn Walker, Heng Ji, and Amanda Stent, editors, Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 2227–2237, New Orleans, Louisiana, June 2018. Association for Computational Linguistics.
dc.relation.references	Rupesh Kumar Srivastava, Klaus Greff, and Jürgen Schmidhuber. Highway networks. CoRR, abs/1505.00387, 2015.
dc.rights.acceso	Abierto (Texto Completo)
dc.rights.accessrights	OpenAccess
dc.subject	CNN
dc.subject	LSTM
dc.subject	Highway network
dc.subject	BiLM
dc.subject	Polisemia
dc.subject	NLP
dc.subject.keyword	CNN
dc.subject.keyword	LSTM
dc.subject.keyword	Highway network
dc.subject.keyword	BiLM
dc.subject.keyword	Polysemy
dc.subject.keyword	NLP
dc.subject.lemb	Matemáticas -- Tesis y disertaciones académicas
dc.subject.lemb	Aprendizaje automático (Inteligencia artificial) -- Aplicaciones
dc.subject.lemb	Métodos de simulación
dc.subject.lemb	Polisemia -- Matemáticas
dc.subject.lemb	Procesamiento del lenguaje natural	spa
dc.subject.lemb	Redes neuronales recurrentes bidireccionales	spa
dc.title	Incrustaciones contextualizadas de palabras con ELMO
dc.title.titleenglish	Contextualized word inlays with ELMO
dc.type	bachelorThesis
dc.type.coar	http://purl.org/coar/resource_type/c_7a1f
dc.type.degree	Monografía
dc.type.driver	info:eu-repo/semantics/bachelorThesis

Archivos

Bloque original

Mostrando 1 - 2 de 2

Nombre:: SeguraGonzálezDavidStiven2024.pdf
Tamaño:: 370.61 KB
Formato:: Adobe Portable Document Format
Descripción:: Trabajo de Grado

Descargar

Nombre:: Licencia de uso y publicación.pdf
Tamaño:: 1.14 MB
Formato:: Adobe Portable Document Format
Descripción:: Licencia de uso y autorización

Descargar

Bloque de licencias

Mostrando 1 - 1 de 1

Nombre:: license.txt
Tamaño:: 7 KB
Formato:: Item-specific license agreed upon to submission
Descripción:

Descargar

Colecciones

Matemáticas