Skip to content
GitLab
Projects
Groups
Snippets
/
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in
Toggle navigation
Menu
Open sidebar
SSHOC
data-ingestion
Commits
1ac8583d
Commit
1ac8583d
authored
Feb 22, 2022
by
Seungbin Yim
Browse files
Changed item property name
parent
364b5a22
Changes
3
Hide whitespace changes
Inline
Side-by-side
openaire/src/rest/sshoc_adapter.py
View file @
1ac8583d
...
...
@@ -262,6 +262,7 @@ class SshocAdapter(object):
items
.
append
(
Triple
(
subj
=
item
[
'subject'
][
'persistentId'
],
pred
=
item
[
'relation'
][
'code'
],
obj
=
item
[
'object'
][
'persistentId'
]))
return
items
def
map_attributes
(
self
,
source
,
target
):
...
...
@@ -297,9 +298,9 @@ class SshocAdapter(object):
def
__to_external_ids
(
key
,
source
):
external_ids
=
[]
for
external_id
in
source
[
key
]:
item_external_id
=
ItemExternalIdId
(
code
=
external_id
[
'
service_
identifier'
][
'code'
])
item_external_id
=
ItemExternalIdId
(
code
=
external_id
[
'identifier
Service
'
][
'code'
])
external_ids
.
append
(
ItemExternalIdCore
(
service_identifier
=
item_external_id
,
identifier
=
external_id
[
'
service_identifier'
][
'
identifier'
]))
identifier
=
external_id
[
'identifier'
]))
return
external_ids
@
staticmethod
...
...
repositories/extraction/.gitignore
View file @
1ac8583d
...
...
@@ -8,6 +8,8 @@ publication_retrieval/__pycache__/
publication_retrieval/config.INI
publication_retrieval/test/config.INI
publication_retrieval/test/output/**/*
publication_retrieval/candidates/analyse.pkl
publication_retrieval/relations/added_relations.pkl
publication_retrieval/output/**
publication_retrieval/pdf/**
ner_ml/**/*
\ No newline at end of file
repositories/extraction/ner_ml/README.md
View file @
1ac8583d
...
...
@@ -2,6 +2,11 @@
You need prodigy installed.
Tested with python version 3.8.4
# DATASET
# TRAINING
The manual model was trained using 1000 manual annotations with the following scores :
`prodigy train ner ann_manual en_vectors_web_lg --output ./tools_model_manual --eval-split 0.2 --n-iter 20`
...
...
Write
Preview
Supports
Markdown
0%
Try again
or
attach a new file
.
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment