Small modifications to enhance the baseline performance like dev EM = 75%#1
Merged
Small modifications to enhance the baseline performance like dev EM = 75%#1
Conversation
akeyhero
force-pushed
the
fix-bugs-on-making-spans
branch
from
7941903 to
48ccd5a
Compare
akeyhero
commented
Mar 1, 2022
| " answer_start_index = ctx_start\n", | ||
| " answer_end_index = len(offsets) - 1\n", | ||
| " while offsets[answer_start_index][0] < start_char:\n", | ||
| " while offsets[answer_start_index][1] < start_char:\n", |
Owner
Author
There was a problem hiding this comment.
One may not like this change, but I prefer inclusive answer chunks.
e.g.:
Original answer: 九十分
Previous answer chunk: 九十
Proposed answer chunk: 九十分間
akeyhero
commented
Mar 1, 2022
| "\n", | ||
| " for i in range(0, input_len - max_seq_len + stride, stride):\n", | ||
| " step = max_seq_len - question_len - stride\n", | ||
| " for i in range(0, max(context_len - stride, step), step):\n", |
Owner
Author
There was a problem hiding this comment.
A stride is an overlapping token length in the Hugging Face manner.
akeyhero
commented
Mar 1, 2022
| " val += [padding] * pad_len\n", | ||
| " return val\n", | ||
| "\n", | ||
| " for i in range(0, input_len - max_seq_len + stride, stride):\n", |
Owner
Author
There was a problem hiding this comment.
This range will be empty when input_len <= max_seq_len - stride
akeyhero
changed the title
akeyhero
changed the title
akeyhero
changed the title
akeyhero
changed the title
akeyhero
commented
Mar 1, 2022
Comment on lines
-488
to
-489
| " while offsets[answer_end_index][1] > start_char + len(answer):\n", | ||
| " answer_end_index -= 1\n", |
Owner
Author
There was a problem hiding this comment.
We will get a smaller index number by 1 when the following token length is >= 2.
akeyhero
changed the title
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
1 participant
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.
Thank you for sharing the great Japanese dataset!
I would like to share my changes to make baseline performance better by 10%+ (in exact match).
Inference log:
Performance by types: