A single model that parses Universal Dependencies across 75 languages. Given a sentence, jointly predicts part-of-speech tags, morphology tags, lemmas, and dependency trees.
If you are seeing poor fine-tuning evaluation UAS/LAS scores, then this additional info might help.
It should take about 10 epochs to start seeing good scores coming from all the metrics, and 80 epochs to be competitive with UDPipe Future. If it's still not showing this, then there might be something off about your training.
One caveat is that if you use a subset of treebanks for fine-tuning instead of all 124 UD v2.3 treebanks, you must modify the configuration file. Make sure to tune the learning rate scheduler in your config to the number of training steps. Copy the udify_bert_finetune_multilingual.json config and modify the "warmup_steps" and "start_step" values. A good initial choice would be to set both to be equal to the number of training batches of one epoch (run the training script first to see the batches remaining).
If you are seeing poor fine-tuning evaluation UAS/LAS scores, then this additional info might help.
It should take about 10 epochs to start seeing good scores coming from all the metrics, and 80 epochs to be competitive with UDPipe Future. If it's still not showing this, then there might be something off about your training.
One caveat is that if you use a subset of treebanks for fine-tuning instead of all 124 UD v2.3 treebanks, you must modify the configuration file. Make sure to tune the learning rate scheduler in your config to the number of training steps. Copy the
udify_bert_finetune_multilingual.json
config and modify the"warmup_steps"
and"start_step"
values. A good initial choice would be to set both to be equal to the number of training batches of one epoch (run the training script first to see the batches remaining).