55   Artículos

 
en línea
Xin Tian and Yuan Meng    
Multi-relational graph neural networks (GNNs) have found widespread application in tasks involving enhancing knowledge representation and knowledge graph (KG) reasoning. However, existing multi-relational GNNs still face limitations in modeling the excha... ver más
Revista: Applied Sciences    Formato: Electrónico

 
en línea
Varsha S. Lalapura, Veerender Reddy Bhimavarapu, J. Amudha and Hariram Selvamurugan Satheesh    
The Recurrent Neural Networks (RNNs) are an essential class of supervised learning algorithms. Complex tasks like speech recognition, machine translation, sentiment classification, weather prediction, etc., are now performed by well-trained RNNs. Local o... ver más
Revista: Algorithms    Formato: Electrónico

 
en línea
Jungha Son and Boyoung Kim    
The rapid global expansion of ChatGPT, which plays a crucial role in interactive knowledge sharing and translation, underscores the importance of comparative performance assessments in artificial intelligence (AI) technology. This study concentrated on t... ver más
Revista: Information    Formato: Electrónico

 
en línea
Yanna Sang, Yuan Chen and Juwei Zhang    
Neural machine translation has achieved good translation results, but needs further improvement in low-resource and domain-specific translation. To this end, the paper proposed to incorporate source language syntactic information into neural machine tran... ver más
Revista: Applied Sciences    Formato: Electrónico

 
en línea
Célia Tavares, Luciana Oliveira, Pedro Duarte and Manuel Moreira da Silva    
According to a recent study by OpenAI, Open Research, and the University of Pennsylvania, large language models (LLMs) based on artificial intelligence (AI), such as generative pretrained transformers (GPTs), may have potential implications for the job m... ver más
Revista: Informatics    Formato: Electrónico

 
en línea
Yonghua Wen, Junjun Guo, Zhiqiang Yu and Zhengtao Yu    
Parallel sentences play a crucial role in various NLP tasks, particularly for cross-lingual tasks such as machine translation. However, due to the time-consuming and laborious nature of manual construction, many low-resource languages still suffer from a... ver más
Revista: Information    Formato: Electrónico

 
en línea
Atnafu Lambebo Tonja, Olga Kolesnikova, Alexander Gelbukh and Grigori Sidorov    
Despite the many proposals to solve the neural machine translation (NMT) problem of low-resource languages, it continues to be difficult. The issue becomes even more complicated when few resources cover only a single domain. In this paper, we discuss the... ver más
Revista: Applied Sciences    Formato: Electrónico

 
en línea
Ivan Kosyanenko,Roman Bolbakov     Pág. 53 - 59
In today's team-based software development, good commit messages - comments on changes made in natural language - are essential. The metric for evaluating a commit message is its relevance. A good commit message should not only describe the changes made,... ver más
Revista: International Journal of Open Information Technologies    Formato: Electrónico

 
en línea
Kaustubh Mani Tripathi, Pooja Kamat, Shruti Patil, Ruchi Jayaswal, Swati Ahirrao and Ketan Kotecha    
This research paper focuses on developing an effective gesture-to-text translation system using state-of-the-art computer vision techniques. The existing research on sign language translation has yet to utilize skin masking, edge detection, and feature e... ver más
Revista: Applied System Innovation    Formato: Electrónico

 
en línea
Zohreh Madhoushi, Abdul Razak Hamdan and Suhaila Zainudin    
Advancements in text representation have produced many deep language models (LMs), such as Word2Vec and recurrent-based LMs. However, there are scarce works that focus on detecting implicit sentiments with a small amount of labelled data because there ar... ver más
Revista: Information    Formato: Electrónico

« Anterior     Página: 1 de 3     Siguiente »