metadata

license: mit
datasets:
  - best2009
  - scb_mt_enth_2020
  - oscar
  - wikipedia
language:
  - th
widget:
  - text: วัน ที่ _ 12 _ มีนาคม นี้ _ ฉัน จะ ไป <mask> วัดพระแก้ว _ ที่ กรุงเทพ
library_name: transformers

HoogBERTa

This repository includes the Thai pretrained language representation (HoogBERTa_base) and can be used for Feature Extraction and Masked Language Modeling Tasks.

Documentation

Prerequisite

Since we use subword-nmt BPE encoding, input needs to be pre-tokenize using BEST standard before inputting into HoogBERTa

pip install attacut

Getting Start

To initialize the model from hub, use the following commands

from transformers import AutoTokenizer, AutoModel
from attacut import tokenize
import torch

tokenizer = AutoTokenizer.from_pretrained("new5558/HoogBERTa")
model = AutoModel.from_pretrained("new5558/HoogBERTa")

To extract token features, based on the RoBERTa architecture, use the following commands

model.eval()
sentence = "วันที่ 12 มีนาคมนี้ ฉันจะไปเที่ยววัดพระแก้ว ที่กรุงเทพ"
all_sent = []
sentences = sentence.split(" ")
for sent in sentences:
    all_sent.append(" ".join(tokenize(sent)).replace("_","[!und:]"))

sentence = " _ ".join(all_sent)
tokenized_text = tokenizer(sentence, return_tensors = 'pt')
token_ids = tokenized_text['input_ids']

with torch.no_grad():
  features = model(**tokenized_text, output_hidden_states = True).hidden_states[-1]

For batch processing,

model.eval()
sentenceL = ["วันที่ 12 มีนาคมนี้","ฉันจะไปเที่ยววัดพระแก้ว ที่กรุงเทพ"]
inputList = []
for sentX in sentenceL:
  sentences = sentX.split(" ")
  all_sent = []
  for sent in sentences:
      all_sent.append(" ".join(tokenize(sent)).replace("_","[!und:]"))

  sentence = " _ ".join(all_sent)
  inputList.append(sentence)
tokenized_text = tokenizer(inputList, padding = True, return_tensors = 'pt')
token_ids = tokenized_text['input_ids']

with torch.no_grad():
    features = model(**tokenized_text, output_hidden_states = True).hidden_states[-1]

To use HoogBERTa as an embedding layer, use

with torch.no_grad():
  features = model(token_ids, output_hidden_states = True).hidden_states[-1] # where token_ids is a tensor with type "long".

Huggingface Models

HoogBERTaEncoder

HoogBERTa: Feature Extraction and Mask Language Modeling

HoogBERTaMuliTaskTagger:

HoogBERTa-NER-lst20: Named-entity recognition (NER) based on LST20
HoogBERTa-POS-lst20: Part-of-speech tagging (POS) based on LST20
HoogBERTa-SENTENCE-lst20: Clause Boundary Classification based on LST20

Citation

Please cite as:

@inproceedings{porkaew2021hoogberta,
  title = {HoogBERTa: Multi-task Sequence Labeling using Thai Pretrained Language Representation},
  author = {Peerachet Porkaew, Prachya Boonkwan and Thepchai Supnithi},
  booktitle = {The Joint International Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP 2021)},
  year = {2021},
  address={Online}
}

Download full-text PDF
Check out the code on Github