2 papers
cs.CL2025
An Encoder-Integrated PhoBERT with Graph Attention for Vietnamese Token-Level Classification
Ba-Quang Nguyen
We propose a novel neural architecture named TextGraphFuseGAT, which integrates a pretrained transformer encoder (PhoBERT) with Graph Attention Networks for token-level classificat…
cs.CL2025
Dynamic Context-Aware Streaming Pretrained Language Model For Inverse Text Normalization
Luong Ho, Khanh Le, Vinh Pham +3
Inverse Text Normalization (ITN) is crucial for converting spoken Automatic Speech Recognition (ASR) outputs into well-formatted written text, enhancing both readability and usabil…