Monotransquest Da Any En

🚀 TransQuest: Translation Quality Estimation with Cross-lingual Transformers

The goal of Quality Estimation (QE) is to assess the quality of a translation without referring to a reference translation. High-accuracy QE that can be easily deployed for multiple language pairs is a crucial component in many commercial translation workflows due to its numerous potential applications. It can help select the best translation when multiple translation engines are available or inform end-users about the reliability of automatically translated content. Additionally, QE systems can determine whether a translation can be directly published in a specific context, requires human post - editing before publication, or needs to be translated from scratch by a human. Quality estimation can be performed at different levels: document, sentence, and word levels.

With TransQuest, we have open - sourced our research on translation quality estimation, which also won the sentence - level direct assessment quality estimation shared task in WMT 2020. TransQuest outperforms current open - source quality estimation frameworks such as OpenKiwi and DeepQuest.

🚀 Quick Start

Quality Estimation (QE) aims to evaluate translation quality without a reference translation. TransQuest is an open - sourced research project in this area, which has achieved excellent results in relevant tasks.

✨ Features

• Sentence - level Estimation: Conduct sentence - level translation quality estimation in two aspects: predicting post - editing efforts and direct assessment.
• Word - level Estimation: Perform word - level translation quality estimation, capable of predicting the quality of source words, target words, and target gaps.
• High Performance: Outperform current state - of - the - art quality estimation methods like DeepQuest and OpenKiwi in all the languages experimented.
• Pre - trained Models: Provide pre - trained quality estimation models for fifteen language pairs on HuggingFace.

📦 Installation

From pip

pip install transquest

From Source

git clone https://github.com/TharinduDR/TransQuest.git
cd TransQuest
pip install -r requirements.txt

💻 Usage Examples

Basic Usage

import torch
from transquest.algo.sentence_level.monotransquest.run_model import MonoTransQuestModel

model = MonoTransQuestModel("xlmroberta", "TransQuest/monotransquest-da-any_en", num_labels=1, use_cuda=torch.cuda.is_available())
predictions, raw_outputs = model.predict([["Reducerea acestor conflicte este importantă pentru conservare.", "Reducing these conflicts is not important for preservation."]])
print(predictions)

📚 Documentation

For more details, please refer to the following documentation:

1. Installation: Install TransQuest locally using pip.
2. Architectures:
   • Sentence - level Architectures: We have released two architectures, MonoTransQuest and SiameseTransQuest, for sentence - level quality estimation.
   • Word - level Architecture: We have released MicroTransQuest for word - level quality estimation.
3. Examples:
   • Sentence - level Examples
   • Word - level Examples
4. Pre - trained Models:
   • Sentence - level Models
   • Word - level Models
5. Contact: Contact us for any issues with TransQuest.

📄 License

This project is licensed under the apache - 2.0 license.

📚 Citations

If you are using the word - level architecture, please consider citing this paper which is accepted to ACL 2021.

@InProceedings{ranasinghe2021,
author = {Ranasinghe, Tharindu and Orasan, Constantin and Mitkov, Ruslan},
title = {An Exploratory Analysis of Multilingual Word Level Quality Estimation with Cross-Lingual Transformers},
booktitle = {Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics},
year = {2021}
}

If you are using the sentence - level architectures, please consider citing these papers which were presented in COLING 2020 and in WMT 2020 at EMNLP 2020.

@InProceedings{transquest:2020a,
author = {Ranasinghe, Tharindu and Orasan, Constantin and Mitkov, Ruslan},
title = {TransQuest: Translation Quality Estimation with Cross-lingual Transformers},
booktitle = {Proceedings of the 28th International Conference on Computational Linguistics},
year = {2020}
}

@InProceedings{transquest:2020b,
author = {Ranasinghe, Tharindu and Orasan, Constantin and Mitkov, Ruslan},
title = {TransQuest at WMT2020: Sentence-Level Direct Assessment},
booktitle = {Proceedings of the Fifth Conference on Machine Translation},
year = {2020}
}