Skip to content
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

Embeddings from Language Models (ELMo) #1

Merged
merged 2 commits into from
May 10, 2018

Conversation

SuperLinguini
Copy link

Description

Embeddings from Language Models (ELMo)

Checklist

Changes

  • Bidirectional LSTM with each layer output and dropout
  • LSTM Cell with projection, clipping, and residual layers
  • Character-level embeddings with CNNs and highway networks

@cgraywang
Copy link
Owner

Thanks @SuperLinguini , please also merge the logs once it is ready. So the character data loader is no longer needed? https://github.com/SuperLinguini/ELMo-BiLM/blob/char_encoder/data.py
as well as the model.py?
https://github.com/SuperLinguini/ELMo-BiLM/blob/char_encoder/model.py

@SuperLinguini
Copy link
Author

@cgraywang Added the character data loader code. Model code is in word_language_model.py. I'll add the logs as they finish.

@cgraywang
Copy link
Owner

Temporally merged

@cgraywang cgraywang merged commit dc494ae into cgraywang:emlo May 10, 2018
2Rings pushed a commit to 2Rings/gluon-nlp-1 that referenced this pull request Jun 13, 2018
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants