Skip to content

Commit 1e234f4

Browse files
committed
sectionizer configs added for brat (3) and medspaCy/CAS XMI
Three new brat sectionizer configs were added. One for the BigODM corpus and two variants for the Textractor corpus (differing in which normalization engine is used). The last config file works with medspaCy output when written to CAS XMI using cassis.
1 parent 9b95a30 commit 1e234f4

File tree

4 files changed

+63
-0
lines changed

4 files changed

+63
-0
lines changed

brat/sections_big-odm_brat.conf

Lines changed: 12 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,12 @@
1+
[ Document Data ]
2+
Format : .ann .txt
3+
Normalization Engines : SectionOntology
4+
5+
#############################################
6+
## Sections
7+
#############################################
8+
9+
[ Section Header ]
10+
Parent: Header
11+
Short Name: Section
12+
Type Prefix: T

brat/sections_ontology_brat.conf

Lines changed: 12 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,12 @@
1+
[ Document Data ]
2+
Format : .ann .txt
3+
Normalization Engines : ClinicalSectionOntology
4+
5+
#############################################
6+
## Sections
7+
#############################################
8+
9+
[ Section Header ]
10+
Parent: Header
11+
Short Name: SectionHeader
12+
Type Prefix: T

brat/sections_textractor_brat.conf

Lines changed: 12 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,12 @@
1+
[ Document Data ]
2+
Format : .ann .txt
3+
Normalization Engines : Textractor
4+
5+
#############################################
6+
## Sections
7+
#############################################
8+
9+
[ Section Header ]
10+
Parent: Header
11+
Short Name: SectionHeader
12+
Type Prefix: T

medspacy/sections_cas-xmi.conf

Lines changed: 27 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,27 @@
1+
[ XML Namespaces ]
2+
cas : http:///uima/cas.ecore
3+
custom : http:///webanno/custom.ecore
4+
uima : http:///edu/musc/tbic/uima.ecore
5+
6+
[ Document Data ]
7+
Content XPath : ./cas:Sofa
8+
Content Attribute : sofaString
9+
10+
#############################################
11+
## Sections
12+
#############################################
13+
14+
[ Section Header ]
15+
Parent: Header
16+
Short Name: Header
17+
XPath: ./uima:NoteSection
18+
Begin Attr: beginHeader
19+
End Attr: endHeader
20+
21+
[ Section Span ]
22+
Parent: FullSpan
23+
Short Name: FullSpan
24+
XPath: ./uima:NoteSection
25+
Begin Attr: begin
26+
End Attr: end
27+

0 commit comments

Comments
 (0)