/nlp_scripts

Scripts for natural language processing, mostly machine translation
  1. Ruby 75.0%
  2. Python 9.2%
  3. Shell 4.3%
  4. Perl 3.4%
  5. Smalltalk 3.1%
  6. NewLisp 2.6%
  7. Other 2.4%
Switch branches/tags
Nothing to show
Find file
Clone or download

Clone with HTTPS

Use Git or checkout with SVN using the web URL.

Download ZIP

Launching GitHub Desktop...

If nothing happens, download GitHub Desktop and try again.

Launching GitHub Desktop...

If nothing happens, download GitHub Desktop and try again.

Launching Xcode...

If nothing happens, download Xcode and try again.

Launching Visual Studio...

If nothing happens, download the GitHub extension for Visual Studio and try again.

Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Failed to load latest commit information.
nonbreaking_prefixes
test
.gitmodules
LICENSE
README.md
add-ln
add-seg
add-start-end
avg
avg-seg-len
avg-weights
bishuf
bitext-filter-length
bleu-cmp
cdec-hg-to-json
cma
cumul
de-bpe
de-sgm
div
dot
even
feature-dict
filter-illegal
filter-len
filter-tokens
first-upper
fix-utf-8-pua
gigaword-collapse-tags
hadoop-uniq
hist-tok
htmlentities
inv
is-first-lower
kbest-bleu-oracles
kendalls-tau
key-count
kmeans
lang
length-ratio
lin-reg
log-reg
ltok
make-rule-features
max
max-len
median
merge-files
merge-ttable
min
min-max
moses-1best
moving-sum
mult
ng
nn
no-empty
no-non-printables
norm
norm-german
norm-hyphens
normalize-punctuation
normchr
num-tok
odd
overlap
paste-pairs
per-sentence-bleu
per-sentence-bleu-kbest
per-sentence-ter
pot
preprocess
preprocess-no-lower
pt-bloom
push-rules
repetition-rate
round
rule-shapes
sample
select
select-from
shard
sort-features
source-sides
split-kbest
split-lines
split-pipes
sqrt
stanford-parser-run
stddev
strips
substract
sum
tc
tf-idf
tmx-extract.py
to-ascii
toks
toks-per-line
train-test-split
var
vocab
vocab2

README.md