P

Phobert Base V2

Developed by vinai
PhoBERT is the most advanced pretrained language model for Vietnamese, optimized based on RoBERTa, and excels in various Vietnamese NLP tasks.
Downloads 54.89k
Release Time : 4/24/2023

Model Overview

PhoBERT is a large-scale monolingual pretrained language model for Vietnamese, optimized based on the RoBERTa architecture, suitable for various Vietnamese natural language processing tasks.

Model Features

Vietnamese Optimization
The first publicly available large-scale monolingual pretrained language model specifically for Vietnamese
High Performance
Outperforms previous monolingual and multilingual approaches in four Vietnamese NLP tasks
Two Sizes
Offers model choices in two parameter sizes: base (135M) and large (370M)
Professional Segmentation
Uses VnCoreNLP's RDRSegmenter for Vietnamese text preprocessing

Model Capabilities

Vietnamese text understanding
Vietnamese part-of-speech tagging
Vietnamese syntactic analysis
Vietnamese named entity recognition
Vietnamese natural language inference

Use Cases

Academic Research
Vietnamese Linguistic Analysis
Used for research on Vietnamese grammar and syntactic structures
Provides accurate part-of-speech tagging and dependency parsing
Commercial Applications
Vietnamese Text Processing
Used in commercial scenarios such as Vietnamese customer service systems and content analysis
Improves the accuracy and efficiency of Vietnamese text processing
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase