search

grammatical / baselines-emnlp2016

Baseline models, training scripts, and instructions on how to reproduce our results for our state-of-art grammar correction system from M. Junczys-Dowmunt, R. Grundkiewicz: Phrase-based Machine Translation is State-of-the-Art for Automatic Grammatical Error Correction, EMNLP 2016.
MIT License
69 stars 17 forks source link

Training with sparse features #3

Closed allenschmaltz closed 7 years ago

allenschmaltz commented 7 years ago

For training sparse features (as with train/config.sparse.yml):

Line 293 of train/run_cross.perl:

The following file does not exist: $DIR/cross.00/work.err-cor/binmodel.err-cor/moses.mert.ini.sparse

In train/train_smt.perl:

For the esm flag:

$MOSESDIR/bin/ESMSequences (on line 288) does not appear to be available in a standard Moses build. Do you plan to make it available?

emjotde commented 7 years ago

Hi, the ESM was never used in our model. That was an experiment of mine that was supposed to mimic the OSM but based on LCS edits instead of word alignments. You want the OSM which should work with the current scripts. We should remove the esm flag to avoid confusion.

allenschmaltz commented 7 years ago

Thanks for the clarification.