Sen Yang
6 papers in the PaperMetrix corpus
Papers by this author
-
Development of Deep Learning Algorithms, Frameworks and Hardwares
2022 · Lecture notes in electrical engineering
Abstract As the core algorithm of artificial intelligence, deep learning has brought new breakthroughs and opportunities to all walks of life. This paper summarizes the principles of deep learning algorithms such as Autoencoder (AE), Boltzmann …
-
Multi-task Pre-training Language Model for Semantic Network Completion
2023 · ACM Transactions on Asian and Low-Resource Language Information Processing
Semantic networks, exemplified by the knowledge graph, serve as a means to represent knowledge by leveraging the structure of a graph. While the knowledge graph exhibits promising potential in the field of natural language processing, …
-
Parameter-efficient fine-tuning in large language models: a survey of methodologies
2025 · Artificial Intelligence Review
The large language models, as predicted by scaling law forecasts, have made groundbreaking progress in many fields, particularly in natural language generation tasks, where they have approached or even surpassed human levels. However, the unprecedented …
-
Research on Bearing Fault Diagnosis Based on GMNR and ResNet-CABA-MAGRU
2025 · Sensors
Focusing on the problem that it is difficult to maintain a high diagnostic accuracy rate, short running time, and robust generalization capability in the face of a strong-noise environment in rolling bearing fault diagnosis, a …
-
Exploring Pre-trained Language Models for Event Extraction and Generation
2019
Traditional approaches to the task of ACE event extraction usually depend on manually annotated data, which is often laborious to create and limited in size. Therefore, in addition to the difficulty of event extraction itself, …
-
Template-Based Named Entity Recognition Using BART
2021
There is a recent interest in investigating fewshot NER, where the low-resource target domain has different label sets compared with a resource-rich source domain. Existing methods use a similarity-based metric. However, they cannot make full …