This repository was archived by the owner on Nov 22, 2022. It is now read-only.
fix embedding loading issue of Fairseq model #201
Closed
Conversation
This file contains 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
facebook-github-bot
added
the
CLA Signed
jinfengr
force-pushed
the
export-D13475500
branch
from
a8c2448 to
47450b4
Compare
jinfengr
pushed a commit
to jinfengr/pytext
that referenced
this pull request
Jan 22, 2019
Summary: Pull Request resolved: facebookresearch#201 Currently Pytext fairseq model doesn't support add pretrained embeddings. This diff is to add pretrained embeddings and it introduces a 5 absolution point improvement in accuracy in my NLG task (see f90768868). Differential Revision: D13475500 fbshipit-source-id: 4d64750b06632e24381209d06c72ff4038ce1398
jinfengr
force-pushed
the
export-D13475500
branch
from
47450b4 to
b7a6a8c
Compare
jinfengr
pushed a commit
to jinfengr/pytext
that referenced
this pull request
Jan 22, 2019
Summary: Pull Request resolved: facebookresearch#201 Currently Pytext fairseq model doesn't support add pretrained embeddings. This diff is to add pretrained embeddings and it introduces a 5 absolution point improvement in accuracy in my NLG task (see f90768868). Differential Revision: D13475500 fbshipit-source-id: df788428706547810fee873654edd3d0cff8b960
jinfengr
force-pushed
the
export-D13475500
branch
from
b7a6a8c to
106d8b4
Compare
jinfengr
pushed a commit
to jinfengr/pytext
that referenced
this pull request
Jan 22, 2019
Summary: Pull Request resolved: facebookresearch#201 Currently Pytext fairseq model doesn't support add pretrained embeddings. This diff is to add pretrained embeddings and it introduces a 5 absolution point improvement in accuracy in my NLG task (see f90768868). Differential Revision: D13475500 fbshipit-source-id: 5613e271f691e1034509607caedbb09b0cb85dfd
jinfengr
force-pushed
the
export-D13475500
branch
from
106d8b4 to
8c291b5
Compare
jinfengr
pushed a commit
to jinfengr/pytext
that referenced
this pull request
Jan 22, 2019
Summary: Pull Request resolved: facebookresearch#201 Currently Pytext fairseq model doesn't support add pretrained embeddings. This diff is to add pretrained embeddings and it introduces a 5 absolution point improvement in accuracy in my NLG task (see f90768868). Differential Revision: D13475500 fbshipit-source-id: cce324eaa6320fbca5c163878bc0312a6bb671b3
jinfengr
force-pushed
the
export-D13475500
branch
from
8c291b5 to
91c2a3b
Compare
jinfengr
pushed a commit
to jinfengr/pytext
that referenced
this pull request
Jan 23, 2019
Summary: Pull Request resolved: facebookresearch#201 Currently Pytext fairseq model doesn't support add pretrained embeddings. This diff is to add pretrained embeddings and it introduces a 5 absolution point improvement in accuracy in my NLG task (see f90768868). Differential Revision: D13475500 fbshipit-source-id: cc5c8e17a2c249962405f88826f1e9bf803eab97
jinfengr
force-pushed
the
export-D13475500
branch
from
91c2a3b to
366af68
Compare
jinfengr
pushed a commit
to jinfengr/pytext
that referenced
this pull request
Jan 23, 2019
Summary: Pull Request resolved: facebookresearch#201 Currently Pytext fairseq model doesn't support add pretrained embeddings. This diff is to add pretrained embeddings and it introduces a 5 absolution point improvement in accuracy in my NLG task (see f90768868). Differential Revision: D13475500 fbshipit-source-id: 9eba5432e9b00abe8bd53faad75523d9e689302d
jinfengr
force-pushed
the
export-D13475500
branch
from
366af68 to
3fc12fd
Compare
jinfengr
pushed a commit
to jinfengr/pytext
that referenced
this pull request
Jan 23, 2019
Summary: Pull Request resolved: facebookresearch#201 Currently Pytext fairseq model doesn't support add pretrained embeddings. This diff is to add pretrained embeddings and it introduces a 5 absolution point improvement in accuracy in my NLG task (see f90768868). Differential Revision: D13475500 fbshipit-source-id: f60fec92dc153d04cdcf61f593a3d2cca8dceed5
jinfengr
force-pushed
the
export-D13475500
branch
from
3fc12fd to
e8ae709
Compare
jinfengr
pushed a commit
to jinfengr/pytext
that referenced
this pull request
Jan 24, 2019
Summary: Pull Request resolved: facebookresearch#201 Currently Pytext fairseq model doesn't support add pretrained embeddings. This diff is to add pretrained embeddings and it introduces a 5 absolution point improvement in accuracy in my NLG task (see f90768868). Differential Revision: D13475500 fbshipit-source-id: 3717995efdc5b82a0adf42c45d182c882021b97d
Summary: Pull Request resolved: facebookresearch#201 Currently Pytext doesn't support add pretrained embedding in labels field, which would be required by most encoder-decoder models. This diff updated data_handler to read pretrained embeddings in labels field. Reviewed By: seayoung1112 Differential Revision: D13475500 fbshipit-source-id: 520d05a85f1ee519200ca8ce9420b30bed252dc6
jinfengr
force-pushed
the
export-D13475500
branch
from
e8ae709 to
8d24e0a
Compare
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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.
Summary: Currently Pytext fairseq model doesn't support add pretrained embeddings. This diff is to add pretrained embeddings and it introduces a 5 absolution point improvement in accuracy in my NLG task (see f90768868).
Differential Revision: D13475500