Last active
December 22, 2015 23:49
-
-
Save junjiah/6549406 to your computer and use it in GitHub Desktop.
extract causation frame's Cause and Effect role from FrameNet annotated corpus
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
from lxml import etree as ET | |
from itertools import chain | |
import sys | |
if len(sys.argv) > 1: | |
f = open(sys.argv[1]) | |
else: | |
f = open('x.xml') # default xml file | |
# first, remove namespace | |
tree = ET.XML(f.read().replace(' xmlns=', ' xmlnamespace=')) | |
f.close() | |
query = ''' | |
//sentence[annotationSet[ | |
@frameName="Causation"]/layer[ | |
@name="FE" and | |
label[@name="Cause"] and | |
label[@name="Effect"]]] | |
''' | |
sens = tree.xpath(query) | |
check_frame = lambda x : x.get('frameName') == 'Causation' | |
for sen in sens: | |
text = sen.find('text').text | |
print "%-7s : %s" % ("TEXT", text) | |
for i, a in enumerate(filter(check_frame, sen)): | |
print "--- %d ---" % i | |
causes = a.iterfind('layer[@name="FE"]/label[@name="Cause"]') | |
effects = a.iterfind('layer[@name="FE"]/label[@name="Effect"]') | |
for item in chain(causes, effects): | |
s, e = item.get('start'), item.get('end') | |
if s and e: | |
print "%-7s : %s" % (item.get('name').upper(), | |
text[int(s):int(e)+1]) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment