summaryrefslogtreecommitdiff
path: root/python/cdec/scfg/features.py
diff options
context:
space:
mode:
authorVictor Chahuneau <vchahune@cs.cmu.edu>2012-06-04 02:16:59 -0400
committerVictor Chahuneau <vchahune@cs.cmu.edu>2012-06-04 02:16:59 -0400
commit57d8aeaf862bad8516e8aa87eca10fdb75bdcb3a (patch)
tree294dc1d5f6e2c6aed40984adc883160ac79132a2 /python/cdec/scfg/features.py
parent43e7813a1001aa84b821f851b29606b6d98a83ac (diff)
Python module: initial version
Diffstat (limited to 'python/cdec/scfg/features.py')
-rw-r--r--python/cdec/scfg/features.py62
1 files changed, 62 insertions, 0 deletions
diff --git a/python/cdec/scfg/features.py b/python/cdec/scfg/features.py
new file mode 100644
index 00000000..6419cdd8
--- /dev/null
+++ b/python/cdec/scfg/features.py
@@ -0,0 +1,62 @@
+from __future__ import division
+import math
+import sym
+
+def contextless(feature):
+ feature.compute_contextless_score = feature
+ return feature
+
+MAXSCORE = 99
+
+def EgivenF(fphrase, ephrase, paircount, fcount, fsample_count): # p(e|f)
+ return -math.log10(paircount/fcount)
+
+def CountEF(fphrase, ephrase, paircount, fcount, fsample_count):
+ return math.log10(1 + paircount)
+
+def SampleCountF(fphrase, ephrase, paircount, fcount, fsample_count):
+ return math.log10(1 + fsample_count)
+
+def EgivenFCoherent(fphrase, ephrase, paircount, fcount, fsample_count):
+ prob = paircount/fsample_count
+ return -math.log10(prob) if prob > 0 else MAXSCORE
+
+def CoherenceProb(fphrase, ephrase, paircount, fcount, fsample_count):
+ return -math.log10(fcount/fsample_count)
+
+def MaxLexEgivenF(ttable):
+ def feature(fphrase, ephrase, paircount, fcount, fsample_count):
+ fwords = [sym.tostring(w) for w in fphrase if not sym.isvar(w)] + ['NULL']
+ ewords = (sym.tostring(w) for w in ephrase if not sym.isvar(w))
+ def score():
+ for e in ewords:
+ maxScore = max(ttable.get_score(f, e, 0) for f in fwords)
+ yield -math.log10(maxScore) if maxScore > 0 else MAXSCORE
+ return sum(score())
+ return feature
+
+def MaxLexFgivenE(ttable):
+ def feature(fphrase, ephrase, paircount, fcount, fsample_count):
+ fwords = (sym.tostring(w) for w in fphrase if not sym.isvar(w))
+ ewords = [sym.tostring(w) for w in ephrase if not sym.isvar(w)] + ['NULL']
+ def score():
+ for f in fwords:
+ maxScore = max(ttable.get_score(f, e, 1) for e in ewords)
+ yield -math.log10(maxScore) if maxScore > 0 else MAXSCORE
+ return sum(score())
+ return feature
+
+def IsSingletonF(fphrase, ephrase, paircount, fcount, fsample_count):
+ return (fcount == 1)
+
+def IsSingletonFE(fphrase, ephrase, paircount, fcount, fsample_count):
+ return (paircount == 1)
+
+def IsNotSingletonF(fphrase, ephrase, paircount, fcount, fsample_count):
+ return (fcount > 1)
+
+def IsNotSingletonFE(fphrase, ephrase, paircount, fcount, fsample_count):
+ return (paircount > 1)
+
+def IsFEGreaterThanZero(fphrase, ephrase, paircount, fcount, fsample_count):
+ return (paircount > 0.01)