DCSQE
Collection
For the 3 directions (ende, zhen, heen) covered in WMT2023, the model is pre-trained on top of XLMR-L using synthetic data generated by DCSQE.
•
8 items
•
Updated
•
2
Matthews correlation coefficient is set as the best metric to train the word-level task.
Using the DCSQE framework, synthetic data is generated from the WMT2023 parallel corpus for pre-training, and then fine-tuned on the WMT2022 QE EN-DE training set, all implemented with the Fairseq framework.
For a detailed description of the DCSQE framework, please refer to the paper:
Alleviating Distribution Shift in Synthetic Data for Machine Translation Quality Estimation
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for DreamW1ngs/DCSQE-ende-word
Base model
FacebookAI/xlm-roberta-large