From 2a48d73eb794fdd736d1df035c8a31af887cde0a Mon Sep 17 00:00:00 2001
From: Patrick Simianer <p@simianer.de>
Date: Fri, 15 Mar 2013 11:31:18 +0100
Subject: overhauled ruby scripts and examples

---
 training/dtrain/examples/toy/cdec.ini        |   3 ++
 training/dtrain/examples/toy/dtrain.ini      |  13 +++++
 training/dtrain/examples/toy/expected-output |  77 +++++++++++++++++++++++++++
 training/dtrain/examples/toy/grammar.gz      | Bin 0 -> 219 bytes
 training/dtrain/examples/toy/src             |   2 +
 training/dtrain/examples/toy/tgt             |   2 +
 6 files changed, 97 insertions(+)
 create mode 100644 training/dtrain/examples/toy/cdec.ini
 create mode 100644 training/dtrain/examples/toy/dtrain.ini
 create mode 100644 training/dtrain/examples/toy/expected-output
 create mode 100644 training/dtrain/examples/toy/grammar.gz
 create mode 100644 training/dtrain/examples/toy/src
 create mode 100644 training/dtrain/examples/toy/tgt

(limited to 'training/dtrain/examples/toy')

diff --git a/training/dtrain/examples/toy/cdec.ini b/training/dtrain/examples/toy/cdec.ini
new file mode 100644
index 00000000..b14f4819
--- /dev/null
+++ b/training/dtrain/examples/toy/cdec.ini
@@ -0,0 +1,3 @@
+formalism=scfg
+add_pass_through_rules=true
+grammar=grammar.gz
diff --git a/training/dtrain/examples/toy/dtrain.ini b/training/dtrain/examples/toy/dtrain.ini
new file mode 100644
index 00000000..cd715f26
--- /dev/null
+++ b/training/dtrain/examples/toy/dtrain.ini
@@ -0,0 +1,13 @@
+decoder_config=cdec.ini
+input=src
+refs=tgt
+output=-
+print_weights=logp shell_rule house_rule small_rule little_rule PassThrough
+k=4
+N=4
+epochs=2
+scorer=bleu
+sample_from=kbest
+filter=uniq
+pair_sampling=all
+learning_rate=1
diff --git a/training/dtrain/examples/toy/expected-output b/training/dtrain/examples/toy/expected-output
new file mode 100644
index 00000000..1da2aadd
--- /dev/null
+++ b/training/dtrain/examples/toy/expected-output
@@ -0,0 +1,77 @@
+Warning: hi_lo only works with pair_sampling XYX.
+                cdec cfg 'cdec.ini'
+Seeding random number sequence to 1664825829
+
+dtrain
+Parameters:
+                       k 4
+                       N 4
+                       T 2
+                  scorer 'bleu'
+             sample from 'kbest'
+                  filter 'uniq'
+           learning rate 1
+                   gamma 0
+             loss margin 0
+                   pairs 'all'
+          pair threshold 0
+          select weights 'last'
+                  l1 reg 0 'none'
+               max pairs 4294967295
+                cdec cfg 'cdec.ini'
+                   input 'src'
+                    refs 'tgt'
+                  output '-'
+(a dot represents 10 inputs)
+Iteration #1 of 2.
+  2
+WEIGHTS
+              logp = +0
+        shell_rule = -1
+        house_rule = +2
+        small_rule = -2
+       little_rule = +3
+       PassThrough = -5
+        ---
+       1best avg score: 0.5 (+0.5)
+ 1best avg model score: 2.5 (+2.5)
+           avg # pairs: 4
+        avg # rank err: 1.5
+     avg # margin viol: 0
+    non0 feature count: 6
+           avg list sz: 4
+           avg f count: 2.875
+(time 0 min, 0 s/S)
+
+Iteration #2 of 2.
+  2
+WEIGHTS
+              logp = +0
+        shell_rule = -1
+        house_rule = +2
+        small_rule = -2
+       little_rule = +3
+       PassThrough = -5
+        ---
+       1best avg score: 1 (+0.5)
+ 1best avg model score: 5 (+2.5)
+           avg # pairs: 5
+        avg # rank err: 0
+     avg # margin viol: 0
+    non0 feature count: 6
+           avg list sz: 4
+           avg f count: 3
+(time 0 min, 0 s/S)
+
+Writing weights file to '-' ...
+house_rule	2
+little_rule	3
+Glue	-4
+PassThrough	-5
+small_rule	-2
+shell_rule	-1
+done
+
+---
+Best iteration: 2 [SCORE 'bleu'=1].
+This took 0 min.
diff --git a/training/dtrain/examples/toy/grammar.gz b/training/dtrain/examples/toy/grammar.gz
new file mode 100644
index 00000000..8eb0d29e
Binary files /dev/null and b/training/dtrain/examples/toy/grammar.gz differ
diff --git a/training/dtrain/examples/toy/src b/training/dtrain/examples/toy/src
new file mode 100644
index 00000000..87e39ef2
--- /dev/null
+++ b/training/dtrain/examples/toy/src
@@ -0,0 +1,2 @@
+ich sah ein kleines haus
+ich fand ein kleines haus
diff --git a/training/dtrain/examples/toy/tgt b/training/dtrain/examples/toy/tgt
new file mode 100644
index 00000000..174926b3
--- /dev/null
+++ b/training/dtrain/examples/toy/tgt
@@ -0,0 +1,2 @@
+i saw a little house
+i found a little house
-- 
cgit v1.2.3