diff options
author | Patrick Simianer <p@simianer.de> | 2012-03-13 09:24:47 +0100 |
---|---|---|
committer | Patrick Simianer <p@simianer.de> | 2012-03-13 09:24:47 +0100 |
commit | ef6085e558e26c8819f1735425761103021b6470 (patch) | |
tree | 5cf70e4c48c64d838e1326b5a505c8c4061bff4a /graehl/NOTES.wfsa | |
parent | 10a232656a0c882b3b955d2bcfac138ce11e8a2e (diff) | |
parent | dfbc278c1057555fda9312291c8024049e00b7d8 (diff) |
merge with upstream
Diffstat (limited to 'graehl/NOTES.wfsa')
-rwxr-xr-x | graehl/NOTES.wfsa | 16 |
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) |