Fullstop Dutch Sonar Punctuation Prediction

🚀 荷兰语标点预测模型

本模型用于预测荷兰语文本的标点符号。我们开发此模型的目的是为了恢复转录口语的标点。

该模型在 SoNaR 数据集 上进行训练。

模型可恢复以下标点符号："." "," "?" "-" ":"

🚀 快速开始

本模型可预测荷兰语文本的标点，主要用于恢复转录口语中的标点。它在 SoNaR 数据集 上训练，能恢复 "." "," "?" "-" ":" 等标点。

📦 安装指南

要开始使用，请从 pypi 安装该包：

pip install deepmultilingualpunctuation

💻 使用示例

基础用法

恢复标点

from deepmultilingualpunctuation import PunctuationModel

model = PunctuationModel(model="oliverguhr/fullstop-dutch-sonar-punctuation-prediction")
text = "hervatting van de zitting ik verklaar de zitting van het europees parlement die op vrijdag 17 december werd onderbroken te zijn hervat"
result = model.restore_punctuation(text)
print(result)

输出

hervatting van de zitting. ik verklaar de zitting van het europees parlement, die op vrijdag 17 december werd onderbroken, te zijn hervat.

预测标签

from deepmultilingualpunctuation import PunctuationModel

model = PunctuationModel(model="oliverguhr/fullstop-dutch-sonar-punctuation-prediction")
text = "hervatting van de zitting ik verklaar de zitting van het europees parlement die op vrijdag 17 december werd onderbroken te zijn hervat"
clean_text = model.preprocess(text)
labled_words = model.predict(clean_text)
print(labled_words)

输出

[['hervatting', '0', 0.99998724], ['van', '0', 0.9999784], ['de', '0', 0.99991274], ['zitting', '.', 0.6771242], ['ik', '0', 0.9999466], ['verklaar', '0', 0.9998566], ['de', '0', 0.9999783], ['zitting', '0', 0.9999809], ['van', '0', 0.99996245], ['het', '0', 0.99997795], ['europees', '0', 0.9999783], ['parlement', ',', 0.9908242], ['die', '0', 0.999985], ['op', '0', 0.99998224], ['vrijdag', '0', 0.9999831], ['17', '0', 0.99997985], ['december', '0', 0.9999827], ['werd', '0', 0.999982], ['onderbroken', ',', 0.9951485], ['te', '0', 0.9999677], ['zijn', '0', 0.99997723], ['hervat', '.', 0.9957053]]

📚 详细文档

模型表现

由于连字符和冒号在很多情况下是可选的，并且可以用逗号或句号代替，因此不同标点符号的模型性能有所差异。该模型取得了以下 F1 分数：

可用模型

官方模型

社区模型

你可以通过设置 model 参数来使用不同的模型：

model = PunctuationModel(model = "oliverguhr/fullstop-dutch-punctuation-prediction")

📄 许可证

本项目采用 MIT 许可证。

🔗 引用方式

@misc{https://doi.org/10.48550/arxiv.2301.03319,
  doi = {10.48550/ARXIV.2301.03319},
  url = {https://arxiv.org/abs/2301.03319},
  author = {Vandeghinste, Vincent and Guhr, Oliver},
  keywords = {Computation and Language (cs.CL), Artificial Intelligence (cs.AI), FOS: Computer and information sciences, FOS: Computer and information sciences, I.2.7},
  title = {FullStop:Punctuation and Segmentation Prediction for Dutch with Transformers},
  publisher = {arXiv},
  year = {2023},  
  copyright = {Creative Commons Attribution Share Alike 4.0 International}
}