A deep learning approach for Named Entity Recognition in Urdu language

Artículo Materias > Ingeniería Universidad Europea del Atlántico > Investigación > Artículos y libros
Universidad Internacional Iberoamericana México > Investigación > Producción Científica
Universidad Internacional Iberoamericana Puerto Rico > Investigación > Producción Científica
Universidad Internacional do Cuanza > Investigación > Producción Científica
Fundación Universitaria Internacional de Colombia > Investigación > Producción Científica Abierto Inglés Named Entity Recognition (NER) is a natural language processing task that has been widely explored for different languages in the recent decade but is still an under-researched area for the Urdu language due to its rich morphology and language complexities. Existing state-of-the-art studies on Urdu NER use various deep-learning approaches through automatic feature selection using word embeddings. This paper presents a deep learning approach for Urdu NER that harnesses FastText and Floret word embeddings to capture the contextual information of words by considering the surrounding context of words for improved feature extraction. The pre-trained FastText and Floret word embeddings are publicly available for Urdu language which are utilized to generate feature vectors of four benchmark Urdu language datasets. These features are then used as input to train various combinations of Long Short-Term Memory (LSTM), Bidirectional LSTM (BiLSTM), Gated Recurrent Unit (GRU), CRF, and deep learning models. The results show that our proposed approach significantly outperforms existing state-of-the-art studies on Urdu NER, achieving an F-score of up to 0.98 when using BiLSTM+GRU with Floret embeddings. Error analysis shows a low classification error rate ranging from 1.24% to 3.63% across various datasets showing the robustness of the proposed approach. The performance comparison shows that the proposed approach significantly outperforms similar existing studies. metadata Khan, Hikmat Ullah; Anam, Rimsha; Anwar, Muhammad Waqas; Jamal, Muhammad Hasan; Bajwa, Usama Ijaz; Diez, Isabel de la Torre; Silva Alvarado, Eduardo René; Soriano Flores, Emmanuel y Ashraf, Imran mail SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, eduardo.silva@funiber.org, emmanuel.soriano@uneatlantico.es, SIN ESPECIFICAR (2024) A deep learning approach for Named Entity Recognition in Urdu language. PLOS ONE, 19 (3). e0300725. ISSN 1932-6203

Texto
journal.pone.0300725.pdf
Available under License Creative Commons Attribution.
Descargar (1MB)

URL Oficial: http://doi.org/10.1371/journal.pone.0300725

Resumen

Named Entity Recognition (NER) is a natural language processing task that has been widely explored for different languages in the recent decade but is still an under-researched area for the Urdu language due to its rich morphology and language complexities. Existing state-of-the-art studies on Urdu NER use various deep-learning approaches through automatic feature selection using word embeddings. This paper presents a deep learning approach for Urdu NER that harnesses FastText and Floret word embeddings to capture the contextual information of words by considering the surrounding context of words for improved feature extraction. The pre-trained FastText and Floret word embeddings are publicly available for Urdu language which are utilized to generate feature vectors of four benchmark Urdu language datasets. These features are then used as input to train various combinations of Long Short-Term Memory (LSTM), Bidirectional LSTM (BiLSTM), Gated Recurrent Unit (GRU), CRF, and deep learning models. The results show that our proposed approach significantly outperforms existing state-of-the-art studies on Urdu NER, achieving an F-score of up to 0.98 when using BiLSTM+GRU with Floret embeddings. Error analysis shows a low classification error rate ranging from 1.24% to 3.63% across various datasets showing the robustness of the proposed approach. The performance comparison shows that the proposed approach significantly outperforms similar existing studies.

Tipo de Documento:	Artículo
Clasificación temática:	Materias > Ingeniería
Divisiones:	Universidad Europea del Atlántico > Investigación > Artículos y libros Universidad Internacional Iberoamericana México > Investigación > Producción Científica Universidad Internacional Iberoamericana Puerto Rico > Investigación > Producción Científica Universidad Internacional do Cuanza > Investigación > Producción Científica Fundación Universitaria Internacional de Colombia > Investigación > Producción Científica
Depositado:	30 May 2024 20:51
Ultima Modificación:	09 Dic 2024 23:30
URI:	https://repositorio.uneatlantico.es/id/eprint/12369

Acciones (logins necesarios)

Ver Objeto

Enzymatic treatment shapes in vitro digestion pattern of phenolic compounds in mulberry juice

The health benefits of mulberry fruit are closely associated with its phenolic compounds. However, the effects of enzymatic treatments on the digestion patterns of these compounds in mulberry juice remain largely unknown. This study investigated the impact of pectinase (PE), pectin lyase (PL), and cellulase (CE) on the release of phenolic compounds in whole mulberry juice. The digestion patterns were further evaluated using an in vitro simulated digestion model. The results revealed that PE significantly increased chlorogenic acid content by 77.8 %, PL enhanced cyanidin-3-O-glucoside by 20.5 %, and CE boosted quercetin by 44.5 %. Following in vitro digestion, the phenolic compound levels decreased differently depending on the treatment, while cyanidin-3-O-rutinoside content increased across all groups. In conclusion, the selected enzymes effectively promoted the release of phenolic compounds in mulberry juice. However, during gastrointestinal digestion, the degradation of phenolic compounds surpassed their enhanced release, with effects varying based on the compound's structure.

Artículos y libros

Peihuan Luo mail , Jian Ai mail , Qiongyao Wang mail , Yihang Lou mail , Zhiwei Liao mail , Francesca Giampieri mail francesca.giampieri@uneatlantico.es, Maurizio Battino mail maurizio.battino@uneatlantico.es, Elwira Sieniawska mail , Weibin Bai mail , Lingmin Tian mail ,

Luo

open

Novel Transfer Learning Approach for Detecting Infected and Healthy Maize Crop Using Leaf Images

Maize is a staple crop worldwide, essential for food security, livestock feed, and industrial uses. Its health directly impacts agricultural productivity and economic stability. Effective detection of maize crop health is crucial for preventing disease spread and ensuring high yields. This study presents VG-GNBNet, an innovative transfer learning model that accurately detects healthy and infected maize crops through a two-step feature extraction process. The proposed model begins by leveraging the visual geometry group (VGG-16) network to extract initial pixel-based spatial features from the crop images. These features are then further refined using the Gaussian Naive Bayes (GNB) model and feature decomposition-based matrix factorization mechanism, which generates more informative features for classification purposes. This study incorporates machine learning models to ensure a comprehensive evaluation. By comparing VG-GNBNet's performance against these models, we validate its robustness and accuracy. Integrating deep learning and machine learning techniques allows VG-GNBNet to capitalize on the strengths of both approaches, leading to superior performance. Extensive experiments demonstrate that the proposed VG-GNBNet+GNB model significantly outperforms other models, achieving an impressive accuracy score of 99.85%. This high accuracy highlights the model's potential for practical application in the agricultural sector, where the precise detection of crop health is crucial for effective disease management and yield optimization.

Artículos y libros

Muhammad Usama Tanveer mail , Kashif Munir mail , Ali Raza mail , Laith Abualigah mail , Helena Garay mail helena.garay@uneatlantico.es, Luis Eduardo Prado González mail uis.prado@uneatlantico.es, Imran Ashraf mail ,

Tanveer

open

A novel and efficient digital image steganography technique using least significant bit substitution

Steganography is used to hide sensitive types of data including images, audio, text, and videos in an invisible way so that no one can detect it. Image-based steganography is a technique that uses images as a cover media for hiding and transmitting sensitive information over the internet. However, image-based steganography is a challenging task due to transparency, security, computational efficiency, tamper protection, payload, etc. Recently, different image steganography methods have been proposed but most of them have reliability issues. Therefore, to solve this issue, we propose an efficient technique based on the Least Significant Bit (LSB). The LSB substitution method minimizes the error rate in the embedding process and is used to achieve greater reliability. Our proposed image-based steganography algorithm incorporates LSB substitution with Magic Matrix, Multi-Level Encryption Algorithm (MLEA), Secret Key (SK), and transposition, flipping. We performed several experiments and the results show that our proposed technique is efficient and achieves efficient results. We tested a total of 165 different RGB images of various dimensions and sizes of hidden information, using various Quality Assessment Metrics (QAMs); A name of few are; Normalized Cross Correlation (NCC), Image Fidelity (IF), Peak Signal Noise Ratio (PSNR), Root Mean Square Error (RMSE), Quality Index (QI), Correlation Coefficient (CC), Structural Similarity Index (SSIM), Mean Square Error (MSE), Entropy, Contrast, and Homogeneity, Image Histogram (IH). We also conducted a comparative analysis with some existing methods as well as security analysis which showed better results. The achieved result demonstrates significant improvements over the current state-of-the-art methods.

Artículos y libros

Shahid Rahman mail , Jamal uddin mail , Hameed Hussain mail , Sabir Shah mail , Abdu Salam mail , Farhan Amin mail , Isabel de la Torre Díez mail , Debora L. Ramírez-Vargas mail debora.ramirez@unini.edu.mx, Julio César Martínez Espinosa mail ulio.martinez@unini.edu.mx,

Rahman

open

External Load Variability in Elite Futsal: Positional Demands and Microcycle Structuring for Player Well-Being and Performance

The aim of this study was to compare the external load of each session along competitive microcycles on an elite futsal team, considering the positions and relationships of the players. The external load of 10 elite players from a First Division team in the Spanish Futsal League (age 27.5 ± 7 years, height 1.73 ± 0.05 m, weight 70.1 ± 3.8 kg) were recorded across 30 microcycles. The players’ external loads were monitored using OLIVER devices. To analyse the external load, Levene’s test was conducted to assess the homogeneity of variances, followed by one-way analysis of variance (ANOVA) to identify differences in dependent variables across the different microcycle days and player positions. Regarding external load during the microcycle, the day with the lowest external load was MD-1, and the days with the highest external load were MD-3 and MD-4. In addition, considering playing positions, pivots exhibited the lowest loads throughout the microcycle, whereas wingers and defenders exhibited the highest loads, depending on the variables analysed. By providing reference values from elite contexts, this study offers practical insights for S&C coaches to optimize microcycles. Furthermore, it contributes to workload management strategies within sport science and public health frameworks, promoting sustainable performance and athlete wellness in futsal.

Artículos y libros

Héctor Gadea-Uribarri mail , Elena Mainer-Pardos mail , Ainhoa Bores Arce mail ainhoa.bores@uneatlantico.es, Rafael Albalad-Aiguabella mail , Sergio López-García mail , Carlos Lago-Fuentes mail carlos.lago@uneatlantico.es,

Gadea-Uribarri

open

Flavonoids for gastrointestinal tract local and associated systemic effects: A review of clinical trials and future perspectives

Background: Flavonoids are naturally occurring dietary phytochemicals with significant antioxidant effects aside from several health benefits. People often consume them in combination with other food components. Compiling data establishes a link between bioactive flavonoids and prevention of several diseases in animal models, including cardiovascular diseases, diabetes, gut dysbiosis, and metabolic dysfunction-associated steatotic liver disease (MASLD). However, numerous clinical studies have demonstrated the ineffectiveness of flavonoids contradicting rodent models, thereby challenging the validity of using flavonoids as dietary supplements. Aim of Review: This review provides a clinical perspective to emphasize the effective roles of dietary flavonoids as well as to summarize their specific mechanisms in animals briefly.

Artículos y libros

Xiaopeng Li mail , Enjun Xie mail , Shumin Sun mail , Jie Shen mail , Yujin Ding mail , Jiaqi Wang mail , Xiaoyu Peng mail , Ruting Zheng mail , Mohamed A. Farag mail , Jianbo Xiao mail ,

Enlaces de interés

Enlaces de interés

TEMÁTICA

ACCESO

IDIOMA

A deep learning approach for Named Entity Recognition in Urdu language

Resumen

Acciones (logins necesarios)

Filtros