diff --git a/scripts/training/train-model.perl b/scripts/training/train-model.perl index 79e118963..cb8561931 100755 --- a/scripts/training/train-model.perl +++ b/scripts/training/train-model.perl @@ -56,22 +56,76 @@ my($_EXTERNAL_BINDIR, $_ONLY_PRINT_GIZA, $_GIZA_EXTENSION, $_REORDERING, - $_REORDERING_SMOOTH, $_INPUT_FACTOR_MAX, $_ALIGNMENT_FACTORS, - $_TRANSLATION_FACTORS, $_REORDERING_FACTORS, $_GENERATION_FACTORS, - $_DECODING_GRAPH_BACKOFF, - $_DECODING_STEPS, $_PARALLEL, $_FACTOR_DELIMITER, @_PHRASE_TABLE, - @_REORDERING_TABLE, @_GENERATION_TABLE, @_GENERATION_TYPE, $_GENERATION_CORPUS, - $_DONT_ZIP, $_MGIZA, $_MGIZA_CPUS, $_SNT2COOC, $_HMM_ALIGN, $_CONFIG, $_OSM, $_OSM_FACTORS, $_POST_DECODING_TRANSLIT, $_TRANSLITERATION_PHRASE_TABLE, - $_HIERARCHICAL,$_XML,$_SOURCE_SYNTAX,$_TARGET_SYNTAX,$_GLUE_GRAMMAR,$_GLUE_GRAMMAR_FILE,$_UNKNOWN_WORD_LABEL_FILE,$_GHKM, - $_GHKM_TREE_FRAGMENTS,$_GHKM_PHRASE_ORIENTATION,$_PHRASE_ORIENTATION_PRIORS_FILE,$_GHKM_SOURCE_LABELS,$_GHKM_SOURCE_LABELS_FILE,$_GHKM_PARTS_OF_SPEECH,$_GHKM_PARTS_OF_SPEECH_FILE, - $_PCFG,@_EXTRACT_OPTIONS,@_SCORE_OPTIONS,$_S2T, - $_ALT_DIRECT_RULE_SCORE_1, $_ALT_DIRECT_RULE_SCORE_2, $_UNKNOWN_WORD_SOFT_MATCHES_FILE, - $_OMIT_WORD_ALIGNMENT,$_FORCE_FACTORED_FILENAMES, - $_MEMSCORE, $_FINAL_ALIGNMENT_MODEL, - $_CONTINUE,$_MAX_LEXICAL_REORDERING,$_LEXICAL_REORDERING_DEFAULT_SCORES,$_DO_STEPS, - @_ADDITIONAL_INI,$_ADDITIONAL_INI_FILE,$_MMSAPT, - @_BASELINE_ALIGNMENT_MODEL, $_BASELINE_EXTRACT, $_BASELINE_ALIGNMENT, - $_DICTIONARY, $_SPARSE_PHRASE_FEATURES, $_EPPEX, $_INSTANCE_WEIGHTS_FILE, $_LMODEL_OOV_FEATURE, $_NUM_LATTICE_FEATURES, $IGNORE, $_FLEXIBILITY_SCORE, $_EXTRACT_COMMAND); + $_REORDERING_SMOOTH, + $_INPUT_FACTOR_MAX, + $_ALIGNMENT_FACTORS, + $_TRANSLATION_FACTORS, + $_REORDERING_FACTORS, + $_GENERATION_FACTORS, + $_DECODING_GRAPH_BACKOFF, + $_DECODING_STEPS, + $_PARALLEL, + $_FACTOR_DELIMITER, + @_PHRASE_TABLE, + @_REORDERING_TABLE, + @_GENERATION_TABLE, + @_GENERATION_TYPE, + $_GENERATION_CORPUS, + $_DONT_ZIP, + $_MGIZA, + $_MGIZA_CPUS, + $_SNT2COOC, + $_HMM_ALIGN, + $_CONFIG, + $_OSM, + $_OSM_FACTORS, + $_POST_DECODING_TRANSLIT, + $_TRANSLITERATION_PHRASE_TABLE, + $_HIERARCHICAL, + $_XML, + $_SOURCE_SYNTAX, + $_TARGET_SYNTAX, + $_GLUE_GRAMMAR, + $_GLUE_GRAMMAR_FILE, + $_UNKNOWN_WORD_LABEL_FILE, + $_GHKM, + $_GHKM_TREE_FRAGMENTS, + $_GHKM_PHRASE_ORIENTATION, + $_PHRASE_ORIENTATION_PRIORS_FILE, + $_GHKM_SOURCE_LABELS, + $_GHKM_SOURCE_LABELS_FILE, + $_GHKM_PARTS_OF_SPEECH, + $_GHKM_PARTS_OF_SPEECH_FILE, + $_PCFG, + @_EXTRACT_OPTIONS, + @_SCORE_OPTIONS, + $_S2T, + $_ALT_DIRECT_RULE_SCORE_1, + $_ALT_DIRECT_RULE_SCORE_2, + $_UNKNOWN_WORD_SOFT_MATCHES_FILE, + $_OMIT_WORD_ALIGNMENT, + $_FORCE_FACTORED_FILENAMES, + $_MEMSCORE, + $_FINAL_ALIGNMENT_MODEL, + $_CONTINUE, + $_MAX_LEXICAL_REORDERING, + $_LEXICAL_REORDERING_DEFAULT_SCORES, + $_DO_STEPS, + @_ADDITIONAL_INI, + $_ADDITIONAL_INI_FILE, + $_MMSAPT, + @_BASELINE_ALIGNMENT_MODEL, + $_BASELINE_EXTRACT, + $_BASELINE_ALIGNMENT, + $_DICTIONARY, + $_SPARSE_PHRASE_FEATURES, + $_EPPEX, + $_INSTANCE_WEIGHTS_FILE, + $_LMODEL_OOV_FEATURE, + $_NUM_LATTICE_FEATURES, + $IGNORE, + $_FLEXIBILITY_SCORE, + $_EXTRACT_COMMAND); my $_BASELINE_CORPUS = ""; my $_CORES = 1; my $debug = 0; # debug this script, do not delete any files in debug mode