summaryrefslogtreecommitdiff
path: root/graehl/NOTES.wfsa
diff options
context:
space:
mode:
authorPatrick Simianer <p@simianer.de>2012-03-13 09:24:47 +0100
committerPatrick Simianer <p@simianer.de>2012-03-13 09:24:47 +0100
commitef6085e558e26c8819f1735425761103021b6470 (patch)
tree5cf70e4c48c64d838e1326b5a505c8c4061bff4a /graehl/NOTES.wfsa
parent10a232656a0c882b3b955d2bcfac138ce11e8a2e (diff)
parentdfbc278c1057555fda9312291c8024049e00b7d8 (diff)
merge with upstream
Diffstat (limited to 'graehl/NOTES.wfsa')
-rwxr-xr-xgraehl/NOTES.wfsa16
1 files changed, 0 insertions, 16 deletions
diff --git a/graehl/NOTES.wfsa b/graehl/NOTES.wfsa
deleted file mode 100755
index b74dc810..00000000
--- a/graehl/NOTES.wfsa
+++ /dev/null
@@ -1,16 +0,0 @@
-left-to-right finite-state models (with heuristic) that depend only on the target string.
-
-http://github.com/jganitkevitch/cdec.git has some progress toward this:
-
-earley_generator.*: make a trie of earley dotted items (from first pass finite parse projected to target side?) and rules for each earley deduction step (is the predict step actually making a hyperedge? or is it marked "active" and so doesn't appear in the result?)
-
-ff_ltor.*: interface for l2r models; needless scoring of "complete" action (only heuristic changes there and heuristics can just be precomputed for all dot-items
-ff_lm.*: ugly clone of regular LM model with l2r interface
-
-apply_models.*: ApplyLeftToRightModelSet
-
-l2r features:
-
-multiple feature ids from single model?
-
-declare markov bound for bottom-up scoring (inside items) wrapper, and "backoff start" state (i.e. empty context, not <s> context)