hfl / chinese-macbert-base

huggingface.co
Total runs: 5.7K
24-hour runs: -442
7-day runs: -1.4K
30-day runs: -4.9K
Model's Last Updated: May 19 2021
fill-mask

Introduction of chinese-macbert-base

Model Details of chinese-macbert-base



GitHub

Please use 'Bert' related functions to load this model!

This repository contains the resources in our paper "Revisiting Pre-trained Models for Chinese Natural Language Processing" , which will be published in " Findings of EMNLP ". You can read our camera-ready paper through ACL Anthology or arXiv pre-print .

Revisiting Pre-trained Models for Chinese Natural Language Processing
Yiming Cui, Wanxiang Che, Ting Liu, Bing Qin, Shijin Wang, Guoping Hu

You may also interested in,

More resources by HFL: https://github.com/ymcui/HFL-Anthology

Introduction

MacBERT is an improved BERT with novel M LM a s c orrection pre-training task, which mitigates the discrepancy of pre-training and fine-tuning.

Instead of masking with [MASK] token, which never appears in the fine-tuning stage, we propose to use similar words for the masking purpose . A similar word is obtained by using Synonyms toolkit (Wang and Hu, 2017) , which is based on word2vec (Mikolov et al., 2013) similarity calculations. If an N-gram is selected to mask, we will find similar words individually. In rare cases, when there is no similar word, we will degrade to use random word replacement.

Here is an example of our pre-training task.

Example
Original Sentence we use a language model to predict the probability of the next word.
MLM we use a language [M] to [M] ##di ##ct the pro [M] ##bility of the next word .
Whole word masking we use a language [M] to [M] [M] [M] the [M] [M] [M] of the next word .
N-gram masking we use a [M] [M] to [M] [M] [M] the [M] [M] [M] [M] [M] next word .
MLM as correction we use a text system to ca ##lc ##ulate the po ##si ##bility of the next word .

Except for the new pre-training task, we also incorporate the following techniques.

  • Whole Word Masking (WWM)
  • N-gram masking
  • Sentence-Order Prediction (SOP)

Note that our MacBERT can be directly replaced with the original BERT as there is no differences in the main neural architecture.

For more technical details, please check our paper: Revisiting Pre-trained Models for Chinese Natural Language Processing

Citation

If you find our resource or paper is useful, please consider including the following citation in your paper.

@inproceedings{cui-etal-2020-revisiting,
    title = "Revisiting Pre-Trained Models for {C}hinese Natural Language Processing",
    author = "Cui, Yiming  and
      Che, Wanxiang  and
      Liu, Ting  and
      Qin, Bing  and
      Wang, Shijin  and
      Hu, Guoping",
    booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Findings",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/2020.findings-emnlp.58",
    pages = "657--668",
}

Runs of hfl chinese-macbert-base on huggingface.co

5.7K
Total runs
-442
24-hour runs
-822
3-day runs
-1.4K
7-day runs
-4.9K
30-day runs

More Information About chinese-macbert-base huggingface.co Model

More chinese-macbert-base license Visit here:

https://choosealicense.com/licenses/apache-2.0

chinese-macbert-base huggingface.co

chinese-macbert-base huggingface.co is an AI model on huggingface.co that provides chinese-macbert-base's model effect (), which can be used instantly with this hfl chinese-macbert-base model. huggingface.co supports a free trial of the chinese-macbert-base model, and also provides paid use of the chinese-macbert-base. Support call chinese-macbert-base model through api, including Node.js, Python, http.

chinese-macbert-base huggingface.co Url

https://huggingface.co/hfl/chinese-macbert-base

hfl chinese-macbert-base online free

chinese-macbert-base huggingface.co is an online trial and call api platform, which integrates chinese-macbert-base's modeling effects, including api services, and provides a free online trial of chinese-macbert-base, you can try chinese-macbert-base online for free by clicking the link below.

hfl chinese-macbert-base online free url in huggingface.co:

https://huggingface.co/hfl/chinese-macbert-base

chinese-macbert-base install

chinese-macbert-base is an open source model from GitHub that offers a free installation service, and any user can find chinese-macbert-base on GitHub to install. At the same time, huggingface.co provides the effect of chinese-macbert-base install, users can directly use chinese-macbert-base installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

chinese-macbert-base install url in huggingface.co:

https://huggingface.co/hfl/chinese-macbert-base

Url of chinese-macbert-base

chinese-macbert-base huggingface.co Url

Provider of chinese-macbert-base huggingface.co

hfl
ORGANIZATIONS

Other API from hfl

huggingface.co

Total runs: 49.6K
Run Growth: 14.4K
Growth Rate: 29.04%
Updated: May 19 2021
huggingface.co

Total runs: 4.2K
Run Growth: 185
Growth Rate: 4.34%
Updated: May 19 2021
huggingface.co

Total runs: 986
Run Growth: 35
Growth Rate: 3.55%
Updated: March 05 2024
huggingface.co

Total runs: 361
Run Growth: -407
Growth Rate: -112.74%
Updated: November 15 2022
huggingface.co

Total runs: 254
Run Growth: -138
Growth Rate: -54.33%
Updated: May 19 2021
huggingface.co

Total runs: 151
Run Growth: 32
Growth Rate: 21.19%
Updated: January 24 2022
huggingface.co

Total runs: 134
Run Growth: 74
Growth Rate: 55.22%
Updated: February 24 2022
huggingface.co

Total runs: 81
Run Growth: -63
Growth Rate: -77.78%
Updated: November 15 2022
huggingface.co

Total runs: 59
Run Growth: -264
Growth Rate: -293.33%
Updated: May 19 2021
huggingface.co

Total runs: 53
Run Growth: -48
Growth Rate: -90.57%
Updated: November 17 2022
huggingface.co

Total runs: 26
Run Growth: 8
Growth Rate: 30.77%
Updated: February 21 2022
huggingface.co

Total runs: 20
Run Growth: -10
Growth Rate: -50.00%
Updated: January 24 2022
huggingface.co

Total runs: 19
Run Growth: -10
Growth Rate: -52.63%
Updated: November 15 2022
huggingface.co

Total runs: 13
Run Growth: -39
Growth Rate: -300.00%
Updated: January 24 2022
huggingface.co

Total runs: 7
Run Growth: 1
Growth Rate: 14.29%
Updated: March 09 2023
huggingface.co

Total runs: 7
Run Growth: -10
Growth Rate: -142.86%
Updated: May 19 2021
huggingface.co

Total runs: 7
Run Growth: 1
Growth Rate: 14.29%
Updated: March 09 2023