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.

Sign up for GitHub

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

Jump to bottom

Parser for Acknowledgments #510

Closed
wants to merge 42 commits into from
Closed

Parser for Acknowledgments #510

wants to merge 42 commits into from

Conversation

tantikristanti
Copy link
Collaborator

@tantikristanti tantikristanti commented Oct 16, 2019 •
edited by lfoppiano
Loading

A branch containing a model for parsing acknowledgment section both for a raw string text and for the Pdf files. Result from the DESIR Code sprint 2.

@tantikristanti
branch for Desir Second Code Sprint Project
133b695 
Former-commit-id: 56e406e
@tantikristanti
add acknowledgment traniner classes
ac6500b 
Former-commit-id: fc63217
@tantikristanti
add crfpp-templates file
e4c9650 
Former-commit-id: a93f2c2
@tantikristanti
fix TEIAcknowledgmentSaxParser
bd84807 
Former-commit-id: a13700a
@tantikristanti
train acknowledgment corpus
161340a 
Former-commit-id: 527da50
@tantikristanti
training acknowledgment corpus and fix codes
3348fc7 
Former-commit-id: 359c58c
@tantikristanti
training acknowledgment corpus and fix codes
6832b23 
Former-commit-id: cb7d9f4
@tantikristanti
web service and documentation for acknowledgment model
e4d3f42 
Former-commit-id: 2ab14dd
@tantikristanti
add testAcknowledgementParser test module in EngineTest class
304151e 
Former-commit-id: c8069f4
@tantikristanti
add acknowledgment processing results in TEI format for PDF documents
a078c1f 
Former-commit-id: 3606c96
@tantikristanti
Merge branch 'master' into DesirSecondCodeSprint
2e3d78a 
# Conflicts:
#	grobid-core/src/main/java/org/grobid/core/engines/Engine.java
#	grobid-trainer/src/main/java/org/grobid/trainer/TrainerRunner.java


Former-commit-id: eed3c30
@tantikristanti
fix some bugs
a6679aa 
Former-commit-id: 5a503bf
@tantikristanti
merge with branch 'master' into DesirSecondCodeSprint
5867ebc 
Former-commit-id: 6e27524
@tantikristanti
integrate the acknowledgment parser results with other tei results
ed6373d 
Former-commit-id: 3f0176e
@tantikristanti
integrate the acknowledgment parser results with other results
558ec2a 
Former-commit-id: e20237b
@tantikristanti
change the tag for the acknowledment parser results from <ref type = …
01a3a46 
…[label]>[result]<ref/> to <rs type=[label]>[result]<rs/>

Former-commit-id: 8c0934e
@tantikristanti
add bounding box coordinates for acknowledgment parser service
93481e0 
Former-commit-id: c8dd17c
@tantikristanti
bring back the TaggingTokenClusterorTest to as is condition, it's cha…
3d792ae 
…nged by accident

Former-commit-id: daf765a
@tantikristanti
Merge branch 'master' into AcknowledgmentParser_Desir2ndCodeSprint
40f1747 
# Conflicts:
#	grobid-core/src/main/java/org/grobid/core/document/TEIFormatter.java


Former-commit-id: 68c080a
@tantikristanti
sync with master branch
d6ad928 
Former-commit-id: f07628a
@tantikristanti
update the documentation for acknowledgment parser
2cd6eb0 
Former-commit-id: dc7fbb0
@tantikristanti
update documentation regarding annotation for acknowledgment model
beb8c17 
Former-commit-id: 207f89d
lfoppiano
lfoppiano requested changes Oct 18, 2019
View reviewed changes
Copy link
Collaborator

@lfoppiano lfoppiano left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thank you for this PR. I passed through it and added some comments. Please have a look at them.

Also why do you need the clearNLP dictionary data/clearNLP/dictionary-1.3.1.zip?

Thank you

.travis.yml Outdated Show resolved Hide resolved
.zshrc Outdated Show resolved Hide resolved
Brewfile Outdated Show resolved Hide resolved
grobid-core/src/main/java/org/grobid/core/engines/DateParser.java Outdated Show resolved Hide resolved
grobid-core/src/main/java/org/grobid/core/engines/FullTextParser.java Outdated Show resolved Hide resolved
grobid-home/models/acknowledgment/TrainResult.txt Outdated Show resolved Hide resolved
grobid-home/models/date/backup/model.wapiti Outdated Show resolved Hide resolved
grobid-home/models/date/model.wapiti Outdated Show resolved Hide resolved
grobid-trainer/resources/dataset/acknowledgment/evaluation/test.tei.xml Outdated Show resolved Hide resolved
grobid-trainer/src/main/java/org/grobid/trainer/AcknowledgmentTrainer.java Outdated Show resolved Hide resolved
@lfoppiano lfoppiano changed the title Acknowledgment parser desir2nd code sprint Parser for Acknowledgments Oct 18, 2019
@coveralls
Copy link

coveralls commented Oct 18, 2019 •
edited
Loading

Coverage Status

Coverage decreased (-0.1%) to 37.19% when pulling cef620b on AcknowledgmentParser_Desir2ndCodeSprint into 5d3ad03 on master.

@tantikristanti
adapt acknowledgmentParser with a new method using TokenClusteror, fi…
ebea486 
…x all class linked with it, fix the test class as well

Former-commit-id: 21a4ef8
@tantikristanti
fix FeaturesVectoracknowledgment, TEIAcknowledgmentSaxParser and Ackn…
13c7afb 
…owledgmenTrainer classes

Former-commit-id: 4ac6896
@tantikristanti
ignore the test for old acknowledgment parser
6bce577 
Former-commit-id: 3e4171a
@tantikristanti
1) adapt a number of codes in several classes as a consequence of Tag…
7c33564 
…gingTokenClusteror implementation in AcknowledgmentParser class; 2) add new feature vectors for improving acknowledgement model; 3) automatically split data (80/20)-train-evaluate a new acknowledgment model; 4) add new n-fold evaluation results. Old results are still kept for comparison purposes.

Former-commit-id: c85abd9
@kermitt2 kermitt2 force-pushed the AcknowledgmentParser_Desir2ndCodeSprint branch from c85abd9 to 7c33564 Compare October 26, 2019 18:54
@tantikristanti
annotate new 100 acknowledgment examples (generate automatically from…
60fcfa7 
… model 0 and correct them), until identifier: 87409333-188e-4307-bc83-91ef9c691aae
@tantikristanti tantikristanti force-pushed the AcknowledgmentParser_Desir2ndCodeSprint branch 2 times, most recently from 1f9f0c5 to 60fcfa7 Compare November 21, 2019 14:49
@lfoppiano lfoppiano marked this pull request as draft April 17, 2020 05:28
@kermitt2
Copy link
Owner

Si finally covered with PR #1046, with some re-design, re-annotation and more training data.

@kermitt2 kermitt2 closed this Feb 13, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@lfoppiano lfoppiano lfoppiano requested changes

@kermitt2 kermitt2 Awaiting requested review from kermitt2

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
4 participants
@tantikristanti @coveralls @kermitt2 @lfoppiano