From 0b091f3f3f792cc6cbe26e68568aeced79d50064 Mon Sep 17 00:00:00 2001 From: Patrick Simianer
Date: Fri, 14 Oct 2011 15:40:23 +0200
Subject: test
---
dtrain/README | 36 ------------------------------------
1 file changed, 36 deletions(-)
delete mode 100644 dtrain/README
(limited to 'dtrain/README')
diff --git a/dtrain/README b/dtrain/README
deleted file mode 100644
index 997c5ff3..00000000
--- a/dtrain/README
+++ /dev/null
@@ -1,36 +0,0 @@
-TODO
- MULTIPARTITE ranking (108010, 1 vs all, cluster modelscore;score)
- what about RESCORING?
- REMEMBER kbest (merge) weights?
- SELECT iteration with highest (real) BLEU?
- GENERATED data? (multi-task, ability to learn, perfect translation in nbest, at first all modelscore 1)
- CACHING (ngrams for scoring)
- hadoop PIPES imlementation
- SHARED LM (kenlm actually does this!)?
- ITERATION variants
- once -> average
- shuffle resulting weights
- weights AVERAGING in reducer (global Ngram counts)
- BATCH implementation (no update after each Kbest list)
- set REFERENCE for cdec (rescoring)?
- MORE THAN ONE reference for BLEU?
- kbest NICER (do not iterate twice)!? -> shared_ptr?
- DO NOT USE Decoder::Decode (input caching as WordID)!?
- sparse vector instead of vector