asdc/XLM_Temporal_Expression_Normalization

XLM_normalization_BEST_MODEL

This model was trained over the XLM-Large model for temporal expression normalization as a result of the paper "A Novel Methodology for Enhancing Cross-Language and Domain Adaptability in Temporal Expression Normalization"

Model description

More information needed

Intended uses & limitations

This model requires from extra post-processing. The proper code can be found at "https://github.com/asdc-s5/Temporal-expression-normalization-with-fill-mask"

Training and evaluation data

All the information about training, evaluation and benchmarking can be found in the paper "A Novel Methodology for Enhancing Cross-Language and Domain Adaptability in Temporal Expression Normalization"

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 8e-05
• train_batch_size: 20
• eval_batch_size: 20
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.1+cu121
• Datasets 2.15.0
• Tokenizers 0.15.0