From 5c4ef3f9206fd7e1ddfe252132582d854d62f0a4 Mon Sep 17 00:00:00 2001 From: Patrick Simianer Date: Mon, 24 Jun 2013 17:45:32 +0200 Subject: documentation --- training/dtrain/README.md | 11 +++++++++++ training/dtrain/examples/parallelized/dtrain.ini | 2 -- 2 files changed, 11 insertions(+), 2 deletions(-) (limited to 'training') diff --git a/training/dtrain/README.md b/training/dtrain/README.md index 2ab2f232..2bae6b48 100644 --- a/training/dtrain/README.md +++ b/training/dtrain/README.md @@ -17,6 +17,17 @@ To build only parts needed for dtrain do cd training/dtrain/; make ``` +Ideas +----- + * get approx_bleu to work? + * implement minibatches (Minibatch and Parallelization for Online Large Margin Structured Learning) + * learning rate 1/T? + * use an oracle? mira-like (model vs. BLEU), feature repr. of reference!? + * implement lc_bleu properly + * merge kbest lists of previous epochs (as MERT does) + * ``walk entire regularization path'' + * rerank after each update? + Running ------- See directories under test/ . diff --git a/training/dtrain/examples/parallelized/dtrain.ini b/training/dtrain/examples/parallelized/dtrain.ini index f19ef891..0b0932d6 100644 --- a/training/dtrain/examples/parallelized/dtrain.ini +++ b/training/dtrain/examples/parallelized/dtrain.ini @@ -11,6 +11,4 @@ pair_sampling=XYX hi_lo=0.1 select_weights=last print_weights=Glue WordPenalty LanguageModel LanguageModel_OOV PhraseModel_0 PhraseModel_1 PhraseModel_2 PhraseModel_3 PhraseModel_4 PhraseModel_5 PhraseModel_6 PassThrough -# newer version of the grammar extractor use different feature names: -#print_weights=Glue WordPenalty LanguageModel LanguageModel_OOV PhraseModel_0 PhraseModel_1 PhraseModel_2 PhraseModel_3 PhraseModel_4 PhraseModel_5 PhraseModel_6 PassThrough decoder_config=cdec.ini -- cgit v1.2.3