summaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2017-12-03filter-lenPatrick Simianer
2017-12-03hist-tok: +xPatrick Simianer
2017-12-03rmPatrick Simianer
2017-11-28vocab2Patrick Simianer
2017-11-27fix select-fromPatrick Simianer
2017-11-11repetition ratePatrick Simianer
2017-11-11cleanupPatrick Simianer
2017-11-10rr: fixPatrick Simianer
2017-11-10rr: fixPatrick Simianer
2017-11-10+xPatrick Simianer
2017-11-10rrPatrick Simianer
2017-11-09rmPatrick Simianer
2017-11-08mteval-14.plPatrick Simianer
2017-11-08de-sgm: use egrep instead of grep for compat.Patrick Simianer
2017-08-04moses' multi-bleu.perlPatrick Simianer
2017-08-04Merge branch 'master' of github.com:pks/nlp_scriptsPatrick Simianer
2017-08-04hist-tokPatrick Simianer
2017-08-04de-bpePatrick Simianer
2017-08-04cumulPatrick Simianer
2017-08-04cmpPatrick Simianer
2017-08-04avg-seg-lenPatrick Simianer
2017-08-04per-sentence-bleu: fixPatrick Simianer
2017-08-04de-sgm: fixPatrick Simianer
2017-07-05overlapPatrick Simianer
2017-06-21filter-illegalPatrick Simianer
2016-11-04rename, remove non nlp stuffPatrick Simianer
2016-08-18non-windowed RRPatrick Simianer
2016-08-18take-memPatrick Simianer
2016-08-18non-windowed RRPatrick Simianer
2016-07-05mvPatrick Simianer
2015-12-23push_rules: push rule weightsPatrick Simianer
2015-12-23source_sides: get source side from translation rulePatrick Simianer
2015-12-23make_rule_features: produce cdec's rule features (ids and bigrams) from a ↵Patrick Simianer
grammar
2015-12-23hadoop_uniq: uniq with hadoop-streamingPatrick Simianer
2015-12-23toks_per_line: # tokens per linePatrick Simianer
2015-12-19corrected stddevPatrick Simianer
2015-11-12Merge branch 'master' of github.com:pks/scriptsPatrick Simianer
2015-11-12READMEPatrick Simianer
2015-11-12preprocessing without lowercasingPatrick Simianer
2015-11-12normalize on char levelPatrick Simianer
2015-11-12map lines to number of token they containPatrick Simianer
2015-11-12script to normalize hyphensPatrick Simianer
2015-11-12script to remove private use area charsPatrick Simianer
2015-11-12add moses' truecaserPatrick Simianer
2015-11-12sample: tab as separatorPatrick Simianer
2015-06-10undo unfortunate variable naming: cfg -> conf!Patrick Simianer
2015-05-30fake_svm_light: invert data in svm light formatPatrick Simianer
2015-05-29feature_dict, convert_to_svmlight_format: stderr outputPatrick Simianer
2015-05-29tf-idf: glob handlingPatrick Simianer
2015-05-29add_ln: add line numbers, filter_features: filter text reps of sparse ↵Patrick Simianer
vectors, split_*: split kbest lists and by line