summaryrefslogtreecommitdiff
path: root/report/promise_power.txt
diff options
context:
space:
mode:
Diffstat (limited to 'report/promise_power.txt')
-rw-r--r--report/promise_power.txt25
1 files changed, 0 insertions, 25 deletions
diff --git a/report/promise_power.txt b/report/promise_power.txt
deleted file mode 100644
index 8c328b7a..00000000
--- a/report/promise_power.txt
+++ /dev/null
@@ -1,25 +0,0 @@
-cdec option "promise_power"
-
-po::value<double>()->default_value(0)
-
-Give more beam budget to more promising previous-pass nodes when pruning - but
-allocate the same average beams. 0 means off, 1 means beam proportional to
-inside*outside prob, n means nth power (affects just --cubepruning_pop_limit).
-note: for the same poplimit, this gives more search error unless very close to 0
-(recommend disabled; even 0.01 is slightly worse than 0) which is a bad sign and
-suggests this isn't doing a good job; further it's slightly slower to LM cube
-rescore with 0.01 compared to 0, as well as giving (very insignificantly) lower
-BLEU. TODO: test under more conditions, or try idea with different formula, or
-prob. cube beams.
-
-
-with urdu mt09 2pass 1st pass tuned w/ unigram, prelm_beam_prune=1 scale_prune_srclen
-
-promise_power: BLEU rescoring time
-0: 20.21 1.8s
-0.01: 20.16 1.9s
-0.1: 20.11 2.0s
-(insignificant differences)
-
-10: 19.7 1.1s
-(faster but much worse bleu)