Views
No views yet
from transformers import AutoTokenizer, AutoModelForMaskedLM
tokenizer = AutoTokenizer.from_pretrained("rinna/japanese-roberta-base", use_fast=False)
tokenizer.do_lower_case = True # due to some bug of tokenizer config loading
model = AutoModelForMaskedLM.from_pretrained("rinna/japanese-roberta-base")[CLS][CLS] token before the sentence for the model to correctly encode it, as it is used during the model training.[MASK] after tokenization[MASK] in an input string and B) replacing a token with [MASK] after tokenization will yield different token sequences, and thus different prediction results. It is more appropriate to use [MASK] after tokenization (as it is consistent with how the model was pretrained). However, the Huggingface Inference API only supports typing [MASK] in the input string and produces less robust predictions.position_ids as an argument explicitlyposition_ids are not provided for a Roberta* model, Huggingface's transformers will automatically construct it but start from padding_idx instead of 0 (see issue and function create_position_ids_from_input_ids() in Huggingface's implementation), which unfortunately does not work as expected with rinna/japanese-roberta-base since the padding_idx of the corresponding tokenizer is not 0. So please be sure to constrcut the position_ids by yourself and make it start from position id 0.# original text
text = "4年に1度オリンピックは開かれる。"
# prepend [CLS]
text = "[CLS]" + text
# tokenize
tokens = tokenizer.tokenize(text)
print(tokens) # output: ['[CLS]', '▁4', '年に', '1', '度', 'オリンピック', 'は', '開かれる', '。']
# mask a token
masked_idx = 5
tokens[masked_idx] = tokenizer.mask_token
print(tokens) # output: ['[CLS]', '▁4', '年に', '1', '度', '[MASK]', 'は', '開かれる', '。']
# convert to ids
token_ids = tokenizer.convert_tokens_to_ids(tokens)
print(token_ids) # output: [4, 1602, 44, 24, 368, 6, 11, 21583, 8]
# convert to tensor
import torch
token_tensor = torch.LongTensor([token_ids])
# provide position ids explicitly
position_ids = list(range(0, token_tensor.size(1)))
print(position_ids) # output: [0, 1, 2, 3, 4, 5, 6, 7, 8]
position_id_tensor = torch.LongTensor([position_ids])
# get the top 10 predictions of the masked token
with torch.no_grad():
outputs = model(input_ids=token_tensor, position_ids=position_id_tensor)
predictions = outputs[0][0, masked_idx].topk(10)
for i, index_t in enumerate(predictions.indices):
index = index_t.item()
token = tokenizer.convert_ids_to_tokens([index])[0]
print(i, token)
"""
0 総会
1 サミット
2 ワールドカップ
3 フェスティバル
4 大会
5 オリンピック
6 全国大会
7 党大会
8 イベント
9 世界選手権
"""1@misc{rinna-japanese-roberta-base,
2 title = {rinna/japanese-roberta-base},
3 author = {Zhao, Tianyu and Sawada, Kei},
4 url = {https://huggingface.co/rinna/japanese-roberta-base}
5}
6
7@inproceedings{sawada2024release,
8 title = {Release of Pre-Trained Models for the {J}apanese Language},
9 author = {Sawada, Kei and Zhao, Tianyu and Shing, Makoto and Mitsui, Kentaro and Kaga, Akio and Hono, Yukiya and Wakatsuki, Toshiaki and Mitsuda, Koh},
10 booktitle = {Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)},
11 month = {5},
12 year = {2024},
13 pages = {13898--13905},
14 url = {https://aclanthology.org/2024.lrec-main.1213},
15 note = {\url{https://arxiv.org/abs/2404.01657}}
16}