/

• .gitmodules
• LICENSE
• README.md
• add_ln
• add_seg
• add_start_end
• avg
• avg_weights
• cdec_hg_to_json
• compound-splitter.perl
• convert_to_svmlight_format
• de-sgm
• dense_features.txt
• detruecase.perl
• div
• dot
• even
• fake_svm_light
• feature_dict
• filter_by_rule_shape
• filter_features
• first_lower
• fix-utf-8-pua
• gigaword_collapse_tags
• hadoop_uniq
• htmlentities
• kbest_bleu_oracles
• kendalls_tau
• key_count
• kmeans
• lin_reg
• log_reg
• lowercase.perl
• ltok
• make_rule_features
• max
• max_len
• median
• mem_usage
• merge_files
• merge_ttable
• min
• min_max
• moses_1best
• mult
• ng
• nn
• no_empty
• no_non_printables
• nonbreaking_prefixes
• norm
• norm_german
• norm_hyphens
• normalize_punctuation
• normchr
• num_tok
• odd
• paste_pairs
• per_sentence_bleu
• per_sentence_bleu_kbest
• per_sentence_ter
• pot
• preprocess
• preprocess_no_lower
• pt_bloom
• round
• ruby_eval
• rule_shapes
• sample
• select
• select_from
• shard
• sort_features
• source_sides
• split_kbest
• split_lines
• split_pipes
• sqrt
• stanford_parser_run
• stddev
• strips
• sum
• tc
• test
• tf-idf
• to_ascii
• tokenizer-no-escape.perl
• toks
• toks_per_line
• train-truecaser.perl
• train_test_split
• truecase.perl
• var
• vocab
• wrap-xml.perl