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
-rwxr-xr-x	NFC	160	log plain
-rw-r--r--	README.md	117	log plain
-rwxr-xr-x	add-index	129	log plain
-rwxr-xr-x	add-ln	90	log plain
-rwxr-xr-x	add-seg	1073	log plain
-rwxr-xr-x	add-start-end	139	log plain
-rwxr-xr-x	avg	360	log plain
-rwxr-xr-x	avg-seg-len	129	log plain
-rwxr-xr-x	avg-weights	590	log plain
-rwxr-xr-x	bishuf	398	log plain
-rwxr-xr-x	bitext-filter-length	2163	log plain
-rwxr-xr-x	biuniq	477	log plain
-rwxr-xr-x	bleu-cmp	468	log plain
-rwxr-xr-x	cdec-hg-to-json	2185	log plain
-rwxr-xr-x	chars	110	log plain
-rwxr-xr-x	cma	395	log plain
-rwxr-xr-x	cumul	727	log plain
-rwxr-xr-x	de-bpe	44	log plain
-rwxr-xr-x	de-sgm	585	log plain
-rwxr-xr-x	div	116	log plain
-rwxr-xr-x	dot	135	log plain
-rwxr-xr-x	even	141	log plain
-rwxr-xr-x	exclude	226	log plain
-rwxr-xr-x	feature-dict	414	log plain
-rwxr-xr-x	filter-illegal	344	log plain
-rwxr-xr-x	filter-len	458	log plain
-rwxr-xr-x	filter-tokens	319	log plain
-rwxr-xr-x	first-upper	119	log plain
-rwxr-xr-x	fix-utf-8-pua	149	log plain
-rwxr-xr-x	gigaword-collapse-tags	651	log plain
-rwxr-xr-x	hadoop-uniq	247	log plain
-rwxr-xr-x	hist-tok	290	log plain
-rwxr-xr-x	htmlentities	185	log plain
-rwxr-xr-x	inv	626	log plain
-rwxr-xr-x	is-first-lower	143	log plain
-rwxr-xr-x	joint-set	349	log plain
-rwxr-xr-x	kbest-bleu-oracles	1462	log plain
-rwxr-xr-x	kendalls-tau	1503	log plain
-rwxr-xr-x	key-count	196	log plain
-rwxr-xr-x	kmeans	3137	log plain
-rwxr-xr-x	lang	1464	log plain
-rwxr-xr-x	langid-polyglot	405	log plain
-rwxr-xr-x	length-ratio	196	log plain
-rwxr-xr-x	lin-reg	1873	log plain
-rwxr-xr-x	log-reg	1516	log plain
-rwxr-xr-x	ltok	137	log plain
-rwxr-xr-x	make-rule-features	713	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	merge-files	452	log plain
-rwxr-xr-x	merge-ttable	611	log plain
-rwxr-xr-x	min	107	log plain
-rwxr-xr-x	min-max	1256	log plain
-rwxr-xr-x	mkidx	101	log plain
-rwxr-xr-x	moses-1best	187	log plain
-rw-r--r--	moving-average	486	log plain
-rwxr-xr-x	moving-sum	122	log plain
-rwxr-xr-x	mult	98	log plain
-rwxr-xr-x	ng	527	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	84	log plain
-rwxr-xr-x	norm-german	1867	log plain
-rwxr-xr-x	norm-hyphens	50	log plain
-rwxr-xr-x	normalize-punctuation	793	log plain
-rwxr-xr-x	normchr	1435	log plain
-rwxr-xr-x	num-tok	137	log plain
-rwxr-xr-x	odd	141	log plain
-rwxr-xr-x	overlap	318	log plain
-rwxr-xr-x	paste-pairs	228	log plain
-rwxr-xr-x	per-sentence-bleu	643	log plain
-rwxr-xr-x	per-sentence-bleu-kbest	688	log plain
-rwxr-xr-x	per-sentence-ter	797	log plain
-rwxr-xr-x	percentile	271	log plain
-rwxr-xr-x	pot	91	log plain
-rwxr-xr-x	preprocess	356	log plain
-rwxr-xr-x	preprocess-no-lower	314	log plain
-rwxr-xr-x	pt-bloom	498	log plain
-rwxr-xr-x	push-rules	353	log plain
-rwxr-xr-x	remove-devtest	1096	log plain
-rwxr-xr-x	remove-test-from-bitext	1192	log plain
-rwxr-xr-x	repetition-rate	732	log plain
-rwxr-xr-x	round	92	log plain
-rwxr-xr-x	rule-shapes	453	log plain
-rwxr-xr-x	sample	1250	log plain
-rwxr-xr-x	select	436	log plain
-rwxr-xr-x	select-from	736	log plain
-rwxr-xr-x	sentencepiece-decode	122	log plain
-rwxr-xr-x	shard	2430	log plain
-rwxr-xr-x	sort-features	197	log plain
-rwxr-xr-x	source-sides	89	log plain
-rwxr-xr-x	split-kbest	347	log plain
-rwxr-xr-x	split-lines	191	log plain
-rwxr-xr-x	split-pipes	829	log plain
-rwxr-xr-x	sqrt	77	log plain
-rwxr-xr-x	stanford-parser-run	496	log plain
-rwxr-xr-x	stddev	644	log plain
-rwxr-xr-x	strips	68	log plain
-rwxr-xr-x	substract	170	log plain
-rwxr-xr-x	sum	89	log plain
-rwxr-xr-x	tc	99	log plain
d---------	test	272	log plain
-rwxr-xr-x	tf-idf	1398	log plain
-rwxr-xr-x	tmx-extract-original-py2.py	2088	log plain
-rwxr-xr-x	tmx-extract.py	2247	log plain
-rwxr-xr-x	to-ascii	256	log plain
-rwxr-xr-x	toks	147	log plain
-rwxr-xr-x	toks-per-line	253	log plain
-rwxr-xr-x	train-test-split	2201	log plain
-rwxr-xr-x	tsv-exclude	365	log plain
-rwxr-xr-x	tsv-joint-set	1114	log plain
-rwxr-xr-x	tsv-uniq	1173	log plain
-rwxr-xr-x	var	471	log plain
-rwxr-xr-x	vocab	58	log plain
-rwxr-xr-x	vocab2	140	log plain
-rwxr-xr-x	zh-ko-or-ja	351	log plain