H

Hoogberta NER Lst20

Developed by lst-nectec
A pre-trained language model fine-tuned for Thai named entity recognition tasks, based on the LST20 dataset
Downloads 95
Release Time : 4/5/2023

Model Overview

HoogBERTa is a pre-trained language model developed for Thai natural language processing tasks. This version is specifically fine-tuned for named entity recognition (NER) tasks on the LST20 dataset.

Model Features

Thai language optimization
A pre-trained language model specifically optimized for Thai language characteristics
Multi-task support
Supports various tasks including named entity recognition, part-of-speech tagging, and clause boundary classification
Pre-tokenization processing
Uses BEST standard pre-tokenization processing to ensure input quality

Model Capabilities

Thai text processing
Named entity recognition
Part-of-speech tagging
Clause boundary classification

Use Cases

Text analysis
Thai text entity extraction
Identify and classify named entities in Thai text
Can accurately recognize various entity types defined in the LST20 dataset
Language processing
Thai text preprocessing
Provides preprocessing support for downstream NLP tasks
Offers part-of-speech tagging and clause boundary identification features
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase