-
Notifications
You must be signed in to change notification settings - Fork 6.3k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Open Source MLM Implementation in Fairseq #635
Conversation
Summary: Pull Request resolved: facebookresearch#635 Adding a task and relevant models, datasets and criteria needed for training Cross-lingual Language Models similar to Masked Language Model used in XLM (Lample and Conneau, 2019 - https://arxiv.org/abs/1901.07291). Reviewed By: liezl200 Differential Revision: D14943776 fbshipit-source-id: 9835d82e9741c2ff9091f24cdbe4bb4be654c5a5
e9d0158
to
13194a0
Compare
This pull request has been merged in 8776928. |
@kartikayk After this PR, i get this error, It seems some files are missing from this? from fairseq.data.masked_lm_dataset import MaskedLMDataset |
@hanyh I'm working on fixing this right now. Will send out an update soon. Sorry for the inconvenience! |
@kartikayk Thanks for that implementation :+1 I have one question: could you also provide a kind of example that shows a) to load a trained model and b) that returns embeddings for each subtoken in a given sentence from that model? That would really help me :) |
Summary: Pull Request resolved: facebookresearch/fairseq#635 Adding a task and relevant models, datasets and criteria needed for training Cross-lingual Language Models similar to Masked Language Model used in XLM (Lample and Conneau, 2019 - https://arxiv.org/abs/1901.07291). Reviewed By: liezl200 Differential Revision: D14943776 fbshipit-source-id: 3e416a730303d1dd4f5b92550c78db989be27073
Summary: Pull Request resolved: facebookresearch/fairseq#635 Adding a task and relevant models, datasets and criteria needed for training Cross-lingual Language Models similar to Masked Language Model used in XLM (Lample and Conneau, 2019 - https://arxiv.org/abs/1901.07291). Reviewed By: liezl200 Differential Revision: D14943776 fbshipit-source-id: 3e416a730303d1dd4f5b92550c78db989be27073
Add the missing step to add the arguments to the parser.
Summary: Adding a task and relevant models, datasets and criteria needed for training Cross-lingual Language Models similar to Masked Language Model used in XLM (Lample and Conneau, 2019 - https://arxiv.org/abs/1901.07291).
Differential Revision: D14943776