Model Card for Model ID

Fine-tuned multilingual BART model for Czech Grammatical Error Correction.

Model Details

Model Description

Developed by: Satoru Katsumata
Shared by [optional]: [More Information Needed]
Model type: [More Information Needed]
Language(s) (NLP): Czech
License: MIT License
Finetuned from model [optional]: Fairseq multilingual BART-large (mbart.CC25)

Model Sources [optional]

Repository: https://github.com/Katsumata420/generic-pretrained-GEC
Paper [optional]: Stronger Baselines for Grammatical Error Correction Using a Pretrained Encoder-Decoder Model.
Demo [optional]: [More Information Needed]

Uses

Since this model was trained with fairseq, fairseq must be used during inference as well.
More details can be found in the README.

This fine-tuned model must be used with a binary file.
The binary file can be downloaded here.

Direct Use

[More Information Needed]

Downstream Use [optional]

[More Information Needed]

Out-of-Scope Use

[More Information Needed]

Bias, Risks, and Limitations

[More Information Needed]

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

Use the code below to get started with the model.

[More Information Needed]

Training Details

See this README.

Training Data

[More Information Needed]

Training Procedure

Preprocessing [optional]

[More Information Needed]

Training Hyperparameters

Training regime: [More Information Needed]

Speeds, Sizes, Times [optional]

[More Information Needed]

Evaluation

Testing Data, Factors & Metrics

Testing Data

[More Information Needed]

Factors

[More Information Needed]

Metrics

m2scorer
- https://www.comp.nus.edu.sg/~nlp/conll14st.html
- metrics
  - Precision
  - Recall
  - F0.5

Results

This model achieved the following results for AKCES-GEC test data.

Precision: 75.75
Recall: 61.41
F0.5: 72.37

Summary

Model Examination [optional]

[More Information Needed]

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

Hardware Type: [More Information Needed]
Hours used: [More Information Needed]
Cloud Provider: [More Information Needed]
Compute Region: [More Information Needed]
Carbon Emitted: [More Information Needed]

Technical Specifications [optional]

Model Architecture and Objective

[More Information Needed]

Compute Infrastructure

[More Information Needed]

Hardware

[More Information Needed]

Software

[More Information Needed]

Citation [optional]

BibTeX:

@inproceedings{katsumata2020AACL,
    title = {Stronger Baselines for Grammatical Error Correction Using a Pretrained Encoder-Decoder Model},
    author = {Satoru Katsumata and Mamoru Komachi},
    booktitle = {Proceedings of AACL-IJCNLP 2020}
    year = {2020},
}

APA:

[More Information Needed]

Glossary [optional]

[More Information Needed]

More Information [optional]

[More Information Needed]

Model Card Authors [optional]

Satoru Katsumata

Model Card Contact

[More Information Needed]