Welcome to mirror list, hosted at ThFree Co, Russian Federation.

github.com/moses-smt/mosesdecoder.git - Unnamed repository; edit this file 'description' to name the repository.
summaryrefslogtreecommitdiff
path: root/vw
diff options
context:
space:
mode:
authorAles Tamchyna <a.tamchyna@gmail.com>2015-01-09 18:00:36 +0300
committerAles Tamchyna <a.tamchyna@gmail.com>2015-01-09 18:00:36 +0300
commitc8967c840a575f94bf8aa36b84c08773ea50c851 (patch)
tree35d1857a8c3edf5173f5138d50ba8f36b759bc3d /vw
parentf1047978a9f727177c01f7af2136972407a880cd (diff)
updating VW readme
Diffstat (limited to 'vw')
-rw-r--r--vw/README.md13
1 files changed, 12 insertions, 1 deletions
diff --git a/vw/README.md b/vw/README.md
index dd434010b..7326b63d7 100644
--- a/vw/README.md
+++ b/vw/README.md
@@ -76,11 +76,22 @@ You can also use multiple classifiers:
VW0= 0.2
VW1= 0.2
...
+
+Features can use any combination of factors. Provide a comma-delimited list of factors in the `source-factors` or `target-factors` variables to override the default setting (`0`, i.e. the first factor).
Training the classifier
-----------------------
-To train a classifier, run `vwtrainer` (a limited version of the `moses` binary). Configure your features in the `moses.ini` file (see above) and set the `train` flag:
+Training uses `vwtrainer` which is a limited version of the `moses` binary. To train, provide your training data as input in the following format:
+
+ source tokens<tab>target tokens<tab>word alignment
+
+Use Moses format for the word alignment (`0-0 1-0` etc.). Set the input type to 5 (`TabbedSentence`, see above):
+
+ [inputtype]
+ 5
+
+Configure your features in the `moses.ini` file (see above) and set the `train` flag:
[features]
...