Jenny Alexandra Ortiz Zambrano
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Jenny Alexandra Ortiz Zambrano has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Arturo Montejo-Ráez
Computer Science Department CEATIC SINAI Universidad de Jaén 23071 Spain
6 shared publications - César Espin-Riofrio
University of Guayaquil
2 shared publications - Ecuador. Universidad Estatal de Milagro2 shared publications
- Eleanor Alexandra Varela-Tapia
Universidad Estatal de Milagro. Milagro, Ecuador
2 shared publications - Ana Herrera Espinoza1 shared publication
- Belkis Chiquinquirá Cañizales Perdomo
Universidad de Guayaquil
1 shared publication
Latest Publications
- 2 September 2026
- Published by Springer Nature
- p. 249-259
Lexical Complexity Prediction in Ecuadorian Public Texts with GPT-4 and Successor Models: An Approach Using Zero-Shot Learning
- 2 September 2026
- Published by Springer Nature
- p. 249-259
Lexical Complexity Prediction in Ecuadorian Public Texts with GPT-4 and Successor Models: An Approach Using Zero-Shot Learning
- Open Access
- 1 February 2025
- Published by Polo de Capacitacion, Investigacion y Publicacion in Polo del Conocimiento
- Vol. 10 (2) , 861-884
GPT-4 y sus modelos sucesores en la predicción de la complejidad léxica en textos públicos Ecuatorianos mediante Few-Shot Learning
Evaluar la complejidad léxica en documentos utilizando los modelos Generative Pre-trained Transformer (GPT-4, GPT-4o y GPT-4 Turbo) permitió analizar su impacto en la comprensión del lenguaje específicamente en textos estatales ecuatorianos en español. Se aplicó la técnica de few-shot learning en todos los modelos, tomando el conjunto de datos GovAIEc. El enfoque aplicado de la investigación es cuantitativo y descriptivo, con un diseño cuasi experimental. Los modelos se evalúan mediante métricas del error común: MAE, MSE, RMSE. El objetivo de esta investigación es evaluar el rendimiento del modelo GPT-4 y sus modelos sucesores en la predicción de la complejidad léxica en textos públicos ecuatorianos mediante Few-Shot Learning. Los resultados indican que el modelo GPT-4 obtiene un mayor rendimiento frente a sus sucesores con un MAE = 0.2464, mientras que GPT-4o presenta un MAE = 0.3889, y finalmente los resultados aplicando el modelo GPT-4 Turbo dieron un MAE = 0.2540.
- 1 February 2025
- Published by Polo de Capacitacion, Investigacion y Publicacion in Polo del Conocimiento
- Vol. 10 (2) , 861-884
Open AccessGPT-4 y sus modelos sucesores en la predicción de la complejidad léxica en textos públicos Ecuatorianos mediante Few-Shot Learning
Evaluar la complejidad léxica en documentos utilizando los modelos Generative Pre-trained Transformer (GPT-4, GPT-4o y GPT-4 Turbo) permitió analizar su impacto en la comprensión del lenguaje específicamente en textos estatales ecuatorianos en español. Se aplicó la técnica de few-shot learning en todos los modelos, tomando el conjunto de datos GovAIEc. El enfoque aplicado de la investigación es cuantitativo y descriptivo, con un diseño cuasi experimental. Los modelos se evalúan mediante métricas del error común: MAE, MSE, RMSE. El objetivo de esta investigación es evaluar el rendimiento del modelo GPT-4 y sus modelos sucesores en la predicción de la complejidad léxica en textos públicos ecuatorianos mediante Few-Shot Learning. Los resultados indican que el modelo GPT-4 obtiene un mayor rendimiento frente a sus sucesores con un MAE = 0.2464, mientras que GPT-4o presenta un MAE = 0.3889, y finalmente los resultados aplicando el modelo GPT-4 Turbo dieron un MAE = 0.2540.
- Open Access
- 1 February 2025
- Published by Polo de Capacitacion, Investigacion y Publicacion in Polo del Conocimiento
- Vol. 10 (2) , 860
Deep Learning y la arquitectura Transformer: Evaluación del Desempeño de RoBERTa-large-bne en la Predicción de la Complejidad Léxica en Textos Estatales Ecuatorianos
En el ámbito de las instituciones públicas, la accesibilidad y comprensión de los documentos gubernamentales suelen verse afectadas por la complejidad léxica y el uso de lenguaje técnico especializado. Este problema impacta tanto a ciudadanos como a funcionarios, generando malentendidos que pueden reducir la transparencia y dificultar la participación ciudadana. En este estudio, se analiza el desempeño del modelo RoBERTa-large-bne, basado en la arquitectura Transformer, en la predicción de la complejidad léxica en textos estatales ecuatorianos. Para ello, se implementó un ajuste fino del modelo con el fin de optimizar su rendimiento en esta tarea específica. Se llevó a cabo una evaluación comparativa con otros modelos de lenguaje pre-entrenados aplicados en el corpus GovAIEc, cuyos textos corresponden a instituciones estatales del Ecuador. Los resultados obtenidos buscan sentar las bases para el desarrollo de herramientas que faciliten la simplificación de documentos públicos, mejorando su accesibilidad y promoviendo una interacción más eficiente entre la ciudadanía y las instituciones gubernamentales.
- 1 February 2025
- Published by Polo de Capacitacion, Investigacion y Publicacion in Polo del Conocimiento
- Vol. 10 (2) , 860
Open AccessDeep Learning y la arquitectura Transformer: Evaluación del Desempeño de RoBERTa-large-bne en la Predicción de la Complejidad Léxica en Textos Estatales Ecuatorianos
En el ámbito de las instituciones públicas, la accesibilidad y comprensión de los documentos gubernamentales suelen verse afectadas por la complejidad léxica y el uso de lenguaje técnico especializado. Este problema impacta tanto a ciudadanos como a funcionarios, generando malentendidos que pueden reducir la transparencia y dificultar la participación ciudadana. En este estudio, se analiza el desempeño del modelo RoBERTa-large-bne, basado en la arquitectura Transformer, en la predicción de la complejidad léxica en textos estatales ecuatorianos. Para ello, se implementó un ajuste fino del modelo con el fin de optimizar su rendimiento en esta tarea específica. Se llevó a cabo una evaluación comparativa con otros modelos de lenguaje pre-entrenados aplicados en el corpus GovAIEc, cuyos textos corresponden a instituciones estatales del Ecuador. Los resultados obtenidos buscan sentar las bases para el desarrollo de herramientas que faciliten la simplificación de documentos públicos, mejorando su accesibilidad y promoviendo una interacción más eficiente entre la ciudadanía y las instituciones gubernamentales.
- Open Access
- 18 November 2024
- Published by Springer Nature in Neural Computing and Applications
- Vol. 37 (3) , 1171-1187
Deep Encodings vs. Linguistic Features in Lexical Complexity Prediction
In this work, we present a novel approach to lexical complexity prediction (LCP) that combines diverse linguistic features with encodings from deep neural networks. We explore the integration of 23 handcrafted linguistic features with embeddings from two well-known language models: BERT and XLM-RoBERTa. Our method concatenates these features before inputting them into various machine learning algorithms, including SVM, Random Forest, and fine-tuned transformer models. We evaluate our approach using two datasets: CompLex for English (a high-resource language) and CLexIS2 for Spanish (a relatively low-resource language in ), allowing us to study performance issues from a cross-lingual perspective. Our experiments involve different combinations of linguistic features with encodings from pretrained deep learning models, testing both token-based and sequence-related encodings. The results demonstrate the effectiveness of our hybrid approach. For the English CompLex corpus, our best model achieved a mean absolute error (MAE) of 0.0683, representing a 29.2% improvement over using linguistic features alone (MAE 0.0965). On the Spanish CLexIS2 corpus, we achieved an MAE of 0.1323, a 19.4. These findings show that handcrafted linguistic features play a fundamental role in achieving higher performance, particularly when combined with deep learning approaches. Our work suggests that hybrid approaches should be considered over full end-to-end solutions for LCP tasks, especially in multilingual contexts.
- 18 November 2024
- Published by Springer Nature in Neural Computing and Applications
- Vol. 37 (3) , 1171-1187
Open AccessDeep Encodings vs. Linguistic Features in Lexical Complexity Prediction
In this work, we present a novel approach to lexical complexity prediction (LCP) that combines diverse linguistic features with encodings from deep neural networks. We explore the integration of 23 handcrafted linguistic features with embeddings from two well-known language models: BERT and XLM-RoBERTa. Our method concatenates these features before inputting them into various machine learning algorithms, including SVM, Random Forest, and fine-tuned transformer models. We evaluate our approach using two datasets: CompLex for English (a high-resource language) and CLexIS2 for Spanish (a relatively low-resource language in ), allowing us to study performance issues from a cross-lingual perspective. Our experiments involve different combinations of linguistic features with encodings from pretrained deep learning models, testing both token-based and sequence-related encodings. The results demonstrate the effectiveness of our hybrid approach. For the English CompLex corpus, our best model achieved a mean absolute error (MAE) of 0.0683, representing a 29.2% improvement over using linguistic features alone (MAE 0.0965). On the Spanish CLexIS2 corpus, we achieved an MAE of 0.1323, a 19.4. These findings show that handcrafted linguistic features play a fundamental role in achieving higher performance, particularly when combined with deep learning approaches. Our work suggests that hybrid approaches should be considered over full end-to-end solutions for LCP tasks, especially in multilingual contexts.
- Open Access
- 27 December 2022
- Published by MDPI AG in Electronics
- Vol. 12 (1) , 120
Combining Transformer Embeddings with Linguistic Features for Complex Word Identification
Identifying which words present in a text may be difficult to understand by common readers is a well-known subtask in text complexity analysis. The advent of deep language models has also established the new state-of-the-art in this task by means of end-to-end semi-supervised (pre-trained) and downstream training of, mainly, transformer-based neural networks. Nevertheless, the usefulness of traditional linguistic features in combination with neural encodings is worth exploring, as the computational cost needed for training and running such networks is becoming more and more relevant with energy-saving constraints. This study explores lexical complexity prediction (LCP) by combining pre-trained and adjusted transformer networks with different types of traditional linguistic features. We apply these features over classical machine learning classifiers. Our best results are obtained by applying Support Vector Machines on an English corpus in an LCP task solved as a regression problem. The results show that linguistic features can be useful in LCP tasks and may improve the performance of deep learning systems.
- 27 December 2022
- Published by MDPI AG in Electronics
- Vol. 12 (1) , 120
Open AccessCombining Transformer Embeddings with Linguistic Features for Complex Word Identification
Identifying which words present in a text may be difficult to understand by common readers is a well-known subtask in text complexity analysis. The advent of deep language models has also established the new state-of-the-art in this task by means of end-to-end semi-supervised (pre-trained) and downstream training of, mainly, transformer-based neural networks. Nevertheless, the usefulness of traditional linguistic features in combination with neural encodings is worth exploring, as the computational cost needed for training and running such networks is becoming more and more relevant with energy-saving constraints. This study explores lexical complexity prediction (LCP) by combining pre-trained and adjusted transformer networks with different types of traditional linguistic features. We apply these features over classical machine learning classifiers. Our best results are obtained by applying Support Vector Machines on an English corpus in an LCP task solved as a regression problem. The results show that linguistic features can be useful in LCP tasks and may improve the performance of deep learning systems.
- 13 October 2019
- Published by Springer Nature
- p. 167-176
VYTEDU-CW: Difficult Words as a Barrier in the Reading Comprehension of University Students
- 13 October 2019
- Published by Springer Nature
- p. 167-176
VYTEDU-CW: Difficult Words as a Barrier in the Reading Comprehension of University Students
- 23 January 2019
- Published by Springer Nature
- p. 111-123
Reading Comprehension in University Texts: The Metrics of Lexical Complexity in Corpus Analysis in Spanish
- 23 January 2019
- Published by Springer Nature
- p. 111-123
Reading Comprehension in University Texts: The Metrics of Lexical Complexity in Corpus Analysis in Spanish
- 2 October 2018
- Published by Springer Nature
- p. 285-297
Sentiment Analysis in Education Domain: A Systematic Literature Review
- 2 October 2018
- Published by Springer Nature
- p. 285-297
Sentiment Analysis in Education Domain: A Systematic Literature Review