def create_forest(self,line):
try:
self.forest = forest.forest_from_text(line, delete_words=['@UNKNOWN@'])
return True
except forest.TreeFormatException:
self.forest = None
return False
def create_forest(self, line):
try:
self.forest = forest.forest_from_text(line,
delete_words=['@UNKNOWN@'])
return True
except forest.TreeFormatException:
self.forest = None
return False
srcfilename = args[1]
forestfilename = args[0]
reffilenames = args[2:]
srcfile = open(srcfilename)
forestfile = open(forestfilename) if forestfilename != "-" else sys.stdin
reffiles = [open(reffilename) for reffilename in reffilenames]
def output(f):
deriv = f.viterbi_deriv()
hypv = deriv.vector()
hyp = deriv.english()
return "hyp={{{%s}}} derivation={{{%s}}} %s" % (" ".join(sym.tostring(e) for e in hyp), deriv, hypv)
for srcline, forestline, reflines in itertools.izip(srcfile, forestfile, itertools.izip(*reffiles)):
f = forest.forest_from_text(forestline)
# the oracle needs to know how long all the French spans are
for item in f.bottomup():
for ded in item.deds:
# replace rule's French side with correct number of French words
# we don't even bother to use the right number of variables
ded.rule = rule.Rule(ded.rule.lhs,
rule.Phrase([sym.fromstring('<foreign-word>')]*int(ded.dcost['foreign-length'])),
ded.rule.e)
f.reweight(weights)
print "1-best %s" % output(f)
s = sgml.Sentence(srcline.split())
s.fwords = srcline.split()
