624 lines
13 KiB
Text
Executable file
624 lines
13 KiB
Text
Executable file
#############################################################################
|
|
## Copyright (c) 1996, Carnegie Mellon University, Cambridge University,
|
|
## Ronald Rosenfeld and Philip Clarkson
|
|
#############################################################################
|
|
=============================================================================
|
|
=============== This file was produced by the CMU-Cambridge ===============
|
|
=============== Statistical Language Modeling Toolkit ===============
|
|
=============================================================================
|
|
This is a 2-gram language model, based on a vocabulary of 71 words,
|
|
which begins "<s>", "</s>", "a"...
|
|
This is an OPEN-vocabulary model (type 1)
|
|
(OOVs were mapped to UNK, which is treated as any other vocabulary word)
|
|
Absolute discounting was applied.
|
|
1-gram discounting constant : 0.454545
|
|
2-gram discounting constant : 0.633663
|
|
This file is in the ARPA-standard format introduced by Doug Paul.
|
|
|
|
p(wd3|wd1,wd2)= if(trigram exists) p_3(wd1,wd2,wd3)
|
|
else if(bigram w1,w2 exists) bo_wt_2(w1,w2)*p(wd3|wd2)
|
|
else p(wd3|w2)
|
|
|
|
p(wd2|wd1)= if(bigram exists) p_2(wd1,wd2)
|
|
else bo_wt_1(wd1)*p_1(wd2)
|
|
|
|
All probs and back-off weights (bo_wt) are given in log10 form.
|
|
|
|
Data formats:
|
|
|
|
Beginning of data mark: \data\
|
|
ngram 1=nr # number of 1-grams
|
|
ngram 2=nr # number of 2-grams
|
|
|
|
\1-grams:
|
|
p_1 wd_1 bo_wt_1
|
|
\2-grams:
|
|
p_2 wd_1 wd_2
|
|
|
|
end of data mark: \end\
|
|
|
|
\data\
|
|
ngram 1=72
|
|
ngram 2=504
|
|
|
|
\1-grams:
|
|
-3.5221 <UNK> 0.0000
|
|
-98.9928 <s> 0.0000
|
|
-3.5221 </s> 0.0000
|
|
-3.5221 a -0.1367
|
|
-3.5221 april -0.1975
|
|
-3.5221 area -0.1980
|
|
-2.7091 august -0.4919
|
|
-3.5221 code -0.1670
|
|
-3.5221 december -0.1980
|
|
-1.1923 eight 0.2622
|
|
-3.5221 eighteen -0.1978
|
|
-3.5221 eighteenth -0.1910
|
|
-3.5221 eighth -0.1910
|
|
-2.7091 eighty -0.2436
|
|
-2.7091 eleven -0.0994
|
|
-3.5221 eleventh -0.1910
|
|
-1.3369 enter -0.1027
|
|
-3.0698 february -0.1909
|
|
-2.7091 fifteen -0.1065
|
|
-3.0698 fifteenth -0.4920
|
|
-3.5221 fifth -0.1910
|
|
-1.8515 fifty -0.1466
|
|
-2.8530 first -0.6681
|
|
-1.0559 five -0.2462
|
|
-2.0672 forty -0.0705
|
|
-1.1600 four 0.1638
|
|
-2.4429 fourteen -0.2595
|
|
-3.5221 fourth -0.1910
|
|
-2.2790 go -0.2105
|
|
-2.1964 help -0.2008
|
|
-3.0698 hundred -0.1357
|
|
-3.0698 january -0.1974
|
|
-2.8530 july -0.1900
|
|
-3.0698 june -0.1909
|
|
-2.8530 march -0.1903
|
|
-2.8530 may -0.1834
|
|
-1.4228 nine 0.7054
|
|
-1.7883 nineteen -0.9412
|
|
-2.7091 ninety -0.0481
|
|
-3.0698 ninth -0.1835
|
|
-2.0672 no -0.2581
|
|
-2.8530 october -0.1898
|
|
-3.0698 of -0.1828
|
|
-1.5142 oh -0.3316
|
|
-0.8794 one 0.2068
|
|
-2.0401 repeat -0.3613
|
|
-3.0698 second -0.4920
|
|
-2.6012 september -0.1826
|
|
-1.2564 seven 0.2397
|
|
-2.8530 seventeen -0.3638
|
|
-3.5221 seventh -0.1910
|
|
-2.1964 seventy -0.2886
|
|
-1.1498 six 0.1383
|
|
-2.8530 sixteen -0.3561
|
|
-3.5221 sixteenth -0.1910
|
|
-3.5221 sixth -0.1910
|
|
-1.4913 sixty -0.2160
|
|
-2.2357 start -0.3236
|
|
-2.0672 stop -0.2839
|
|
-2.2357 ten -0.2802
|
|
-2.8530 third -0.6681
|
|
-2.8530 thirtieth -0.6681
|
|
-2.0146 thirty -0.1262
|
|
-2.8530 thousand -0.2794
|
|
-1.2313 three 0.2953
|
|
-3.0698 twelfth -0.4920
|
|
-2.3811 twelve -0.1637
|
|
-3.5221 twentieth -0.1910
|
|
-1.7883 twenty -0.1149
|
|
-0.9133 two -0.1824
|
|
-1.9461 yes -0.0598
|
|
-1.8515 zero -0.0435
|
|
|
|
\2-grams:
|
|
-0.4361 a one
|
|
-0.4361 april thirtieth
|
|
-0.4361 area code
|
|
-1.0382 august sixteenth
|
|
-0.2280 august twenty
|
|
-0.4361 code four
|
|
-0.4361 december eighteenth
|
|
-2.5043 eight april
|
|
-2.5043 eight august
|
|
-1.3385 eight eight
|
|
-1.0126 eight enter
|
|
-2.5043 eight fifty
|
|
-1.2009 eight five
|
|
-2.5043 eight forty
|
|
-0.9422 eight four
|
|
-2.5043 eight fourteen
|
|
-2.5043 eight help
|
|
-2.5043 eight hundred
|
|
-2.5043 eight june
|
|
-1.3385 eight nine
|
|
-2.5043 eight no
|
|
-1.6941 eight oh
|
|
-1.3385 eight one
|
|
-1.3385 eight seven
|
|
-1.9326 eight seventy
|
|
-1.4281 eight six
|
|
-1.6941 eight sixty
|
|
-2.5043 eight stop
|
|
-2.5043 eight ten
|
|
-2.5043 eight thirty
|
|
-0.9108 eight three
|
|
-2.5043 eight twelve
|
|
-1.9326 eight twenty
|
|
-1.0126 eight two
|
|
-1.5410 eight zero
|
|
-0.4361 eighteen february
|
|
-0.4361 eighteenth nineteen
|
|
-0.4361 eighth nineteen
|
|
-0.4665 eighty nine
|
|
-1.0382 eighty six
|
|
-1.0382 eighty three
|
|
-1.0382 eleven nine
|
|
-1.0382 eleven one
|
|
-1.0382 eleven seventeen
|
|
-1.0382 eleven sixty
|
|
-0.4361 eleventh nineteen
|
|
-1.0570 enter eight
|
|
-2.3604 enter eighty
|
|
-2.3604 enter fifteen
|
|
-1.2842 enter fifty
|
|
-1.1946 enter five
|
|
-1.5502 enter forty
|
|
-1.1946 enter four
|
|
-2.3604 enter fourteen
|
|
-1.3971 enter nine
|
|
-1.5502 enter ninety
|
|
-1.3971 enter one
|
|
-1.0017 enter seven
|
|
-1.3971 enter seventy
|
|
-1.0570 enter six
|
|
-1.0570 enter sixty
|
|
-1.5502 enter thirty
|
|
-1.7887 enter three
|
|
-2.3604 enter twenty
|
|
-1.1946 enter two
|
|
-2.3604 enter zero
|
|
-0.7371 february eighth
|
|
-0.7371 february nineteen
|
|
-1.0382 fifteen nineteen
|
|
-1.0382 fifteen one
|
|
-1.0382 fifteen sixty
|
|
-1.0382 fifteen thirty
|
|
-0.1655 fifteenth nineteen
|
|
-0.4361 fifth nineteen
|
|
-0.8878 fifty eight
|
|
-1.0409 fifty five
|
|
-1.2794 fifty four
|
|
-0.6853 fifty one
|
|
-1.2794 fifty seven
|
|
-0.7749 fifty six
|
|
-1.8511 fifty sixty
|
|
-1.8511 fifty three
|
|
-1.2794 fifty two
|
|
-0.1030 first nineteen
|
|
-1.6770 five eight
|
|
-1.5640 five enter
|
|
-1.2816 five five
|
|
-1.4744 five four
|
|
-2.6402 five fourteen
|
|
-1.8300 five help
|
|
-2.6402 five may
|
|
-1.4744 five nine
|
|
-2.6402 five ninth
|
|
-2.6402 five october
|
|
-1.4744 five oh
|
|
-0.8952 five one
|
|
-2.6402 five repeat
|
|
-1.6770 five seven
|
|
-1.4002 five six
|
|
-2.6402 five sixteen
|
|
-2.6402 five ten
|
|
-1.4002 five three
|
|
-2.6402 five twenty
|
|
-0.3822 five two
|
|
-1.6770 five yes
|
|
-1.8300 five zero
|
|
-1.6402 forty eight
|
|
-1.0686 forty five
|
|
-1.0686 forty four
|
|
-1.6402 forty nine
|
|
-1.0686 forty one
|
|
-0.8300 forty seven
|
|
-0.8300 forty three
|
|
-1.0686 forty two
|
|
-2.5365 four august
|
|
-1.2331 four eight
|
|
-2.5365 four eleven
|
|
-1.4603 four enter
|
|
-1.7263 four fifty
|
|
-1.3707 four five
|
|
-2.5365 four forty
|
|
-0.9430 four four
|
|
-2.5365 four help
|
|
-1.9648 four january
|
|
-2.5365 four march
|
|
-1.9648 four nine
|
|
-1.9648 four no
|
|
-1.5732 four oh
|
|
-0.7318 four one
|
|
-2.5365 four repeat
|
|
-2.5365 four september
|
|
-1.2965 four seven
|
|
-1.1288 four six
|
|
-1.9648 four sixty
|
|
-1.9648 four stop
|
|
-2.5365 four thousand
|
|
-1.3707 four three
|
|
-2.5365 four twelve
|
|
-1.9648 four twenty
|
|
-0.9138 four two
|
|
-2.5365 four zero
|
|
-1.2812 fourteen a
|
|
-1.2812 fourteen fourteen
|
|
-1.2812 fourteen one
|
|
-1.2812 fourteen repeat
|
|
-0.4710 fourteen sixty
|
|
-0.4361 fourth nineteen
|
|
-0.8644 go enter
|
|
-1.4361 go fifty
|
|
-1.4361 go one
|
|
-0.8644 go repeat
|
|
-1.4361 go stop
|
|
-1.4361 go three
|
|
-0.8644 go yes
|
|
-0.5520 help enter
|
|
-1.5153 help fifty
|
|
-0.9436 help go
|
|
-1.5153 help help
|
|
-1.5153 help one
|
|
-1.5153 help seven
|
|
-1.5153 help three
|
|
-1.5153 help yes
|
|
-0.7371 hundred eighty
|
|
-0.7371 hundred one
|
|
-0.7371 january fifteenth
|
|
-0.7371 january twelfth
|
|
-0.9132 july thirtieth
|
|
-0.9132 july twelfth
|
|
-0.9132 july twenty
|
|
-0.7371 june eleventh
|
|
-0.7371 june twenty
|
|
-0.9132 march third
|
|
-0.9132 march twentieth
|
|
-0.9132 march twenty
|
|
-0.9132 may nineteen
|
|
-0.9132 may ninth
|
|
-0.9132 may twenty
|
|
-2.2750 nine august
|
|
-1.4648 nine eight
|
|
-2.2750 nine eighty
|
|
-2.2750 nine eleven
|
|
-1.1092 nine enter
|
|
-2.2750 nine fifty
|
|
-0.8673 nine five
|
|
-2.2750 nine forty
|
|
-2.2750 nine four
|
|
-2.2750 nine go
|
|
-2.2750 nine help
|
|
-2.2750 nine july
|
|
-2.2750 nine june
|
|
-2.2750 nine nine
|
|
-2.2750 nine nineteen
|
|
-2.2750 nine no
|
|
-2.2750 nine of
|
|
-2.2750 nine oh
|
|
-1.1987 nine one
|
|
-2.2750 nine september
|
|
-1.7033 nine seven
|
|
-2.2750 nine seventy
|
|
-1.0350 nine six
|
|
-2.2750 nine sixty
|
|
-2.2750 nine stop
|
|
-2.2750 nine thirty
|
|
-1.1987 nine three
|
|
-2.2750 nine twenty
|
|
-1.0350 nine two
|
|
-1.7033 nine yes
|
|
-2.2750 nine zero
|
|
-1.3416 nineteen fifty
|
|
-1.3416 nineteen forty
|
|
-1.1030 nineteen seventy
|
|
-0.1474 nineteen sixty
|
|
-1.9132 nineteen twenty
|
|
-1.0382 ninety eight
|
|
-1.0382 ninety five
|
|
-1.0382 ninety four
|
|
-1.0382 ninety six
|
|
-0.7371 ninth of
|
|
-0.7371 ninth sixty
|
|
-0.8300 no enter
|
|
-1.0686 no fifty
|
|
-1.6402 no help
|
|
-0.6770 no one
|
|
-1.6402 no repeat
|
|
-1.6402 no six
|
|
-1.0686 no start
|
|
-1.6402 no three
|
|
-1.6402 no yes
|
|
-0.9132 october first
|
|
-0.9132 october thirtieth
|
|
-0.9132 october twenty
|
|
-0.7371 of september
|
|
-0.7371 of sixty
|
|
-0.7326 oh eight
|
|
-1.1081 oh five
|
|
-1.3741 oh four
|
|
-2.1843 oh nine
|
|
-1.6126 oh oh
|
|
-1.0185 oh one
|
|
-1.1081 oh seven
|
|
-0.7326 oh six
|
|
-1.2210 oh three
|
|
-2.1843 oh twelve
|
|
-0.9443 oh two
|
|
-2.8163 one august
|
|
-1.5763 one eight
|
|
-2.8163 one eleven
|
|
-1.6505 one enter
|
|
-2.8163 one february
|
|
-2.8163 one fifteen
|
|
-1.8531 one fifty
|
|
-0.5328 one five
|
|
-2.8163 one forty
|
|
-1.3246 one four
|
|
-2.8163 one go
|
|
-2.8163 one help
|
|
-2.8163 one hundred
|
|
-2.8163 one july
|
|
-1.4577 one nine
|
|
-2.8163 one ninety
|
|
-2.8163 one no
|
|
-1.3646 one oh
|
|
-1.2229 one one
|
|
-2.8163 one repeat
|
|
-1.0505 one seven
|
|
-1.5763 one six
|
|
-2.8163 one sixteen
|
|
-2.0061 one sixty
|
|
-2.2447 one start
|
|
-2.8163 one stop
|
|
-2.2447 one ten
|
|
-2.2447 one thirty
|
|
-2.2447 one thousand
|
|
-1.2542 one three
|
|
-2.2447 one twenty
|
|
-0.9274 one two
|
|
-2.8163 one yes
|
|
-1.7401 one zero
|
|
-1.0949 repeat enter
|
|
-1.6666 repeat fifty
|
|
-1.6666 repeat five
|
|
-1.6666 repeat forty
|
|
-0.7033 repeat no
|
|
-0.7033 repeat one
|
|
-1.6666 repeat repeat
|
|
-0.8564 repeat stop
|
|
-0.1655 second nineteen
|
|
-1.1351 september fifteenth
|
|
-1.1351 september first
|
|
-1.1351 september nineteen
|
|
-1.1351 september sixth
|
|
-1.1351 september twenty
|
|
-2.4404 seven area
|
|
-1.0818 seven eight
|
|
-1.1371 seven enter
|
|
-2.4404 seven fifteen
|
|
-2.4404 seven fifty
|
|
-1.3642 seven five
|
|
-1.8688 seven forty
|
|
-0.8470 seven four
|
|
-1.8688 seven fourteen
|
|
-2.4404 seven go
|
|
-2.4404 seven may
|
|
-1.3642 seven nine
|
|
-2.4404 seven october
|
|
-1.4772 seven oh
|
|
-1.1371 seven one
|
|
-1.6302 seven seven
|
|
-2.4404 seven seventeen
|
|
-1.3642 seven six
|
|
-1.8688 seven sixty
|
|
-1.4772 seven start
|
|
-1.3642 seven stop
|
|
-1.8688 seven ten
|
|
-1.8688 seven thirty
|
|
-1.6302 seven three
|
|
-2.4404 seven twenty
|
|
-1.2004 seven two
|
|
-1.8688 seven yes
|
|
-0.3416 seventeen fifty
|
|
-0.9132 seventeen thirty
|
|
-0.4361 seventh nineteen
|
|
-1.5153 seventy eight
|
|
-1.5153 seventy enter
|
|
-1.5153 seventy no
|
|
-0.3495 seventy one
|
|
-0.9436 seventy two
|
|
-1.5153 seventy yes
|
|
-0.7238 six eight
|
|
-1.4705 six enter
|
|
-1.3809 six five
|
|
-2.5467 six forty
|
|
-1.1390 six four
|
|
-2.5467 six july
|
|
-1.5834 six nine
|
|
-2.5467 six no
|
|
-1.3809 six oh
|
|
-0.9240 six one
|
|
-2.5467 six repeat
|
|
-2.5467 six september
|
|
-1.3809 six seven
|
|
-2.5467 six seventeen
|
|
-1.0550 six six
|
|
-2.5467 six sixteen
|
|
-1.9750 six sixty
|
|
-2.5467 six start
|
|
-2.5467 six ten
|
|
-1.7365 six thirty
|
|
-1.0550 six three
|
|
-2.5467 six twelve
|
|
-2.5467 six twenty
|
|
-1.1881 six two
|
|
-2.5467 six yes
|
|
-2.5467 six zero
|
|
-0.9132 sixteen forty
|
|
-0.3416 sixteen sixty
|
|
-0.4361 sixteenth nineteen
|
|
-0.4361 sixth nineteen
|
|
-1.1307 sixty eight
|
|
-1.6353 sixty enter
|
|
-2.2070 sixty fifty
|
|
-1.1307 sixty five
|
|
-1.2437 sixty four
|
|
-1.6353 sixty help
|
|
-0.7152 sixty nine
|
|
-0.9670 sixty one
|
|
-0.7993 sixty seven
|
|
-1.6353 sixty six
|
|
-2.2070 sixty start
|
|
-1.1307 sixty three
|
|
-1.3968 sixty two
|
|
-0.6673 start enter
|
|
-1.4775 start go
|
|
-1.4775 start no
|
|
-1.4775 start one
|
|
-0.6673 start repeat
|
|
-0.9058 start six
|
|
-0.4002 stop enter
|
|
-1.6402 stop go
|
|
-0.8300 stop one
|
|
-1.6402 stop repeat
|
|
-1.6402 stop seven
|
|
-1.6402 stop thirty
|
|
-1.6402 stop two
|
|
-1.6402 stop yes
|
|
-1.4775 ten oh
|
|
-0.4013 ten one
|
|
-1.4775 ten seventy
|
|
-1.4775 ten sixty
|
|
-1.4775 ten thirty
|
|
-1.4775 ten twelve
|
|
-1.4775 ten twenty
|
|
-0.1030 third nineteen
|
|
-0.1030 thirtieth nineteen
|
|
-1.1197 thirty eight
|
|
-1.6914 thirty five
|
|
-0.3880 thirty one
|
|
-1.6914 thirty seven
|
|
-1.6914 thirty six
|
|
-1.6914 thirty sixty
|
|
-1.6914 thirty three
|
|
-0.8812 thirty two
|
|
-0.9132 thousand eight
|
|
-0.3416 thousand one
|
|
-2.4655 three december
|
|
-1.2997 three eight
|
|
-2.4655 three eighty
|
|
-2.4655 three eleven
|
|
-1.8938 three enter
|
|
-1.2997 three five
|
|
-1.8938 three forty
|
|
-1.0138 three four
|
|
-2.4655 three fourteen
|
|
-2.4655 three march
|
|
-2.4655 three may
|
|
-1.6553 three nine
|
|
-1.6553 three no
|
|
-1.2997 three oh
|
|
-1.0578 three one
|
|
-2.4655 three repeat
|
|
-2.4655 three september
|
|
-1.5022 three seven
|
|
-2.4655 three seventy
|
|
-1.1068 three six
|
|
-1.8938 three sixty
|
|
-2.4655 three stop
|
|
-2.4655 three ten
|
|
-1.1621 three three
|
|
-2.4655 three twelve
|
|
-1.6553 three twenty
|
|
-0.8720 three two
|
|
-1.8938 three yes
|
|
-1.6553 three zero
|
|
-0.1655 twelfth nineteen
|
|
-1.3392 twelve fifty
|
|
-1.3392 twelve four
|
|
-1.3392 twelve nine
|
|
-1.3392 twelve nineteen
|
|
-1.3392 twelve sixty
|
|
-1.3392 twelve ten
|
|
-0.7675 twelve twenty
|
|
-0.4361 twentieth nineteen
|
|
-0.8370 twenty eight
|
|
-1.9132 twenty fifth
|
|
-1.9132 twenty first
|
|
-1.3416 twenty four
|
|
-1.9132 twenty fourth
|
|
-1.1030 twenty nine
|
|
-1.1030 twenty one
|
|
-1.3416 twenty second
|
|
-1.3416 twenty seven
|
|
-1.9132 twenty seventh
|
|
-1.1030 twenty six
|
|
-1.3416 twenty third
|
|
-1.3416 twenty three
|
|
-1.3416 twenty two
|
|
-1.4238 two eight
|
|
-2.7825 two eighteen
|
|
-1.7062 two enter
|
|
-2.7825 two fifteen
|
|
-1.2541 two five
|
|
-1.1066 two four
|
|
-2.7825 two go
|
|
-2.7825 two help
|
|
-2.7825 two march
|
|
-1.5425 two nine
|
|
-2.7825 two no
|
|
-2.7825 two october
|
|
-1.2907 two oh
|
|
-0.5953 two one
|
|
-2.7825 two repeat
|
|
-1.3307 two seven
|
|
-0.9596 two six
|
|
-2.7825 two sixty
|
|
-2.2108 two ten
|
|
-2.2108 two thirty
|
|
-1.1890 two three
|
|
-2.7825 two twelve
|
|
-2.2108 two twenty
|
|
-0.9091 two two
|
|
-1.6167 two zero
|
|
-0.7951 yes enter
|
|
-1.7583 yes five
|
|
-1.7583 yes four
|
|
-1.1867 yes go
|
|
-0.9481 yes one
|
|
-1.1867 yes repeat
|
|
-1.7583 yes six
|
|
-1.7583 yes start
|
|
-1.7583 yes stop
|
|
-1.7583 yes twenty
|
|
-1.1867 yes two
|
|
-1.1867 yes yes
|
|
-1.8511 zero eight
|
|
-1.2794 zero enter
|
|
-1.8511 zero five
|
|
-1.8511 zero four
|
|
-1.8511 zero nine
|
|
-0.5477 zero one
|
|
-1.2794 zero seven
|
|
-0.6853 zero six
|
|
-1.8511 zero twelve
|
|
-1.2794 zero two
|
|
-1.8511 zero zero
|
|
|
|
\end\
|