summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorPatrick Simianer <p@simianer.de>2011-10-29 19:56:55 +0200
committerPatrick Simianer <p@simianer.de>2011-10-29 19:56:55 +0200
commit0c28b8dc375722c631486377217c6c8a6a362b5a (patch)
tree18e37d4d9152b43066756ed69a2745fcf3dc91f1
parent7417ad2225b4c049cb7cb7122a717e8c8b6e5eaa (diff)
README
-rw-r--r--dtrain/README.md64
-rw-r--r--dtrain/dtrain.cc2
2 files changed, 55 insertions, 11 deletions
diff --git a/dtrain/README.md b/dtrain/README.md
index bc96ed18..3d09393c 100644
--- a/dtrain/README.md
+++ b/dtrain/README.md
@@ -45,7 +45,10 @@ FIXME
-----
merge dtrain part-* files
mapred count shard sents
-
+250 forest sampling is real bad, bug?
+kenlm not portable (i7-2620M vs Intel(R) Xeon(R) CPU E5620 @ 2.40GHz)
+metric reporter of bleu for each shard
+mapred chaining? hamake?
Data
----
@@ -66,16 +69,57 @@ p: prep, e: extract, g: grammar, d: dtrain
Experiments
-----------
-features
- TODO
+grammar stats
+ oov on dev/devtest/test
+ size
+ #rules (uniq)
+ time for building
+ ep: 1.5 days on 278 slots (30 nodes)
+ nc: ~2 hours ^^^
+
+lm stats
+ oov on dev/devtest/test
+ perplex on train/dev/devtest/test
+
+which word alignment?
+ berkeleyaligner
+ giza++ as of Sep 24 2011, mgizapp 0.6.3
+ symgiza as of Oct 1 2011
+ ---
+ randomly sample 100 from train.loo
+ run mira/dtrain for 50/60 iterations
+ w/o lm, wp
+ measure ibm_bleu on exact same sents
+
+stability
+ mira: 100
+ pro: 100
+ vest: 100
+ dtrain: 100
+
+
+pro metaparam
+ (max) iter
+ regularization
+
+mira metaparam
+ (max) iter: 10 (nc???) vs 15 (ep???)
-"lm open better than lm closed when tuned"
+lm?
+ 3-4-5
+ open
+ unk
+ nounk (-100 for unk)
+ --
+ tune or not???
+ lm oov weight pos?
-mira100-10
-mira100-17
+features to try
+ NgramFeatures -> target side ngrams
+ RuleIdentityFeatures
+ RuleNgramFeatures -> source side ngrams from rule
+ RuleShape -> relative orientation of X's and terminals
+ SpanFeatures -> http://www.cs.cmu.edu/~cdyer/wmt11-sysdesc.pdf
+ ArityPenalty -> Arity=0 Arity=1 and Arity=2
-baselines
- mira
- pro
- vest
diff --git a/dtrain/dtrain.cc b/dtrain/dtrain.cc
index 277d4e14..c4f6607d 100644
--- a/dtrain/dtrain.cc
+++ b/dtrain/dtrain.cc
@@ -25,7 +25,7 @@ dtrain_init(int argc, char** argv, po::variables_map* cfg)
("tmp", po::value<string>()->default_value("/tmp"), "temp dir to use")
("select_weights", po::value<string>()->default_value("last"), "output 'best' or 'last' weights ('VOID' to throw away)")
#ifdef DTRAIN_LOCAL
- ("refs,r", po::value<string>(), "references for local mode")
+ ("refs,r", po::value<string>(), "references in local mode")
#endif
("noup", po::value<bool>()->zero_tokens(), "do not update weights");
po::options_description cl("Command Line Options");