nlp_scripts - Mirror of https://github.com/pks/nlp

Mode	Name	Size
-rw-r--r--	.gitmodules	82	log plain
-rw-r--r--	LICENSE	1080	log plain
-rw-r--r--	README.md	265	log plain
-rwxr-xr-x	add_seg	1093	log plain
-rwxr-xr-x	add_start_end	139	log plain
-rwxr-xr-x	avg	355	log plain
-rwxr-xr-x	avg_weights	586	log plain
-rwxr-xr-x	cdec_hg_to_json	2185	log plain
-rwxr-xr-x	compound-splitter.perl	9044	log plain
-rwxr-xr-x	de-sgm	277	log plain
-rwxr-xr-x	dot	135	log plain
-rwxr-xr-x	even	141	log plain
-rwxr-xr-x	filter_by_rule_shape	550	log plain
-rwxr-xr-x	first_lower	143	log plain
-rwxr-xr-x	gigaword_collapse_tags	651	log plain
-rwxr-xr-x	htmlentities	185	log plain
-rwxr-xr-x	kbest_bleu_oracles	1453	log plain
-rwxr-xr-x	key_count	196	log plain
-rwxr-xr-x	kmeans	3126	log plain
-rwxr-xr-x	lin_reg	1864	log plain
-rwxr-xr-x	log_reg	1511	log plain
-rwxr-xr-x	lowercase.perl	120	log plain
-rwxr-xr-x	max	110	log plain
-rwxr-xr-x	max_len	180	log plain
-rwxr-xr-x	median	117	log plain
-rwxr-xr-x	mem_usage	194	log plain
-rwxr-xr-x	merge_files	452	log plain
-rwxr-xr-x	merge_ttable	606	log plain
-rwxr-xr-x	min	107	log plain
-rwxr-xr-x	min_max	1244	log plain
-rwxr-xr-x	moses_1best	187	log plain
-rwxr-xr-x	mult	98	log plain
-rwxr-xr-x	ng	521	log plain
-rwxr-xr-x	nn	72	log plain
-rwxr-xr-x	no_empty	363	log plain
-rwxr-xr-x	no_non_printables	88	log plain
d---------	nonbreaking_prefixes	871	log plain
-rwxr-xr-x	norm_german	1861	log plain
-rwxr-xr-x	normalize_punctuation	793	log plain
-rwxr-xr-x	num_tok	137	log plain
-rwxr-xr-x	odd	141	log plain
-rwxr-xr-x	paste_pairs	228	log plain
-rwxr-xr-x	per_sentence_bleu	630	log plain
-rwxr-xr-x	per_sentence_bleu_kbest	683	log plain
-rwxr-xr-x	per_sentence_ter	810	log plain
-rwxr-xr-x	pot	91	log plain
-rwxr-xr-x	preprocess	356	log plain
-rwxr-xr-x	pt_bloom	493	log plain
-rwxr-xr-x	round	92	log plain
-rwxr-xr-x	ruby_eval	72	log plain
-rwxr-xr-x	rule_shapes	453	log plain
-rwxr-xr-x	sample	1247	log plain
-rwxr-xr-x	select	434	log plain
-rwxr-xr-x	select_from	570	log plain
-rwxr-xr-x	shard	2428	log plain
-rwxr-xr-x	sort_features	197	log plain
-rwxr-xr-x	split_pipes	357	log plain
-rwxr-xr-x	sqrt	77	log plain
-rwxr-xr-x	stanford_parser_run	496	log plain
-rwxr-xr-x	stddev	488	log plain
-rwxr-xr-x	strips	68	log plain
-rwxr-xr-x	sum	89	log plain
-rwxr-xr-x	tc	99	log plain
d---------	test	188	log plain
-rwxr-xr-x	tf-idf	1275	log plain
-rwxr-xr-x	to_ascii	256	log plain
-rwxr-xr-x	tokenizer-no-escape.perl	10147	log plain
-rwxr-xr-x	toks	147	log plain
-rwxr-xr-x	train_test_split	1376	log plain
-rwxr-xr-x	var	466	log plain
-rwxr-xr-x	vocab	125	log plain
-rwxr-xr-x	wrap-xml.perl	934	log plain