Adds Residual X feature, Multi-task learning v1 and SRL configs from dev/v1.2/jy#67
Open
purujitgoyal wants to merge 24 commits into
Open
Adds Residual X feature, Multi-task learning v1 and SRL configs from dev/v1.2/jy#67purujitgoyal wants to merge 24 commits into
purujitgoyal wants to merge 24 commits into
Conversation
…aselines into dev/v1.2/jy
…aselines into dev/v1.2/jy
…aselines into feat/seq-tag
…ction_baselines into feat/seq-tag
…trol it, adds parameters to control cnn structured score
purujitgoyal
changed the title
purujitgoyal
requested review from
dhruvdcoder,
leejayyoon,
wenlongzhao094 and
zhiyangxu-VT
and removed request for
dhruvdcoder
January 9, 2022 22:27
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Residual X feature concats embedded_x with y before passing to global_score.
Sample config at model_configs/srl/ontonotes_seal_nce_bert_residual.jsonnet
Multi-Task v1 assumes tasknn don't has its own tag_projection_layer and will be trained by tasknn-optimizer while both scorenn and sampler/infernece_module train their own tag_projection_layer.
Added a sample config at model_configs/sequence_tagging/conll2003_seal_nce_self_attention_bilstm_multi_task.jsonnet