phrase pair 0.00500851
target phrase 0.004866027
phrase table 0.004772171
baseline phrase 0.004736691
phrase pairs 0.004707001
new phrase 0.004489216
phrase extraction 0.0044467050000000004
standard phrase 0.00441352
bidirectional phrase 0.004293951
phrase tables 0.004292474
phrase extrac 0.004264749
phrase boundaries 0.0042632139999999995
known phrase 0.004260505
phrase 0.00395416
translation models 0.003142572
lexicon translation 0.0030821380000000003
translation probabilities 0.0029948880000000002
machine translation 0.002943396
language model 0.00291109
translation tasks 0.002852621
model features 0.002590058
translation 0.00247201
word alignment 0.002418933
target phrases 0.0022888170000000003
model score 0.002285759
svm model 0.002242436
language pair 0.00208047
sentence pair 0.00207803
side phrases 0.001945317
new phrases 0.001912006
different distribution 0.0018997880000000001
standard word 0.00188829
model 0.00188497
smt training 0.001798958
baseline corpus 0.0017964510000000001
parallel corpus 0.001789607
sentence pairs 0.0017765209999999999
pairs corpus 0.001766761
original phrases 0.001748297
alignment models 0.001660565
propbank data 0.001637397
other language 0.0016362999999999998
training set 0.001611403
new sentence 0.0015587359999999998
new corpus 0.001548976
alignment process 0.001542424
semantic role 0.0014902689999999998
target side 0.001480234
other words 0.0014774340000000001
semantic constraints 0.0014576139999999999
semantic structure 0.001446648
parallel sentences 0.001433888
different information 0.001431505
quality sentence 0.0014211529999999999
semantic structures 0.0013964399999999999
original sentence 0.0013950269999999999
original corpus 0.001385267
semantic frames 0.001383464
whole sentence 0.0013808289999999999
semantic signature 0.001377915
phrases 0.00137695
semantic frame 0.0013752069999999998
semantic roles 0.001373062
semantic sig 0.0013714439999999999
tence pair 0.001363916
fbis corpus 0.001359641
sentence generation 0.0013473369999999999
abundant sentence 0.001333786
labeled sentence 0.0013309149999999998
generated corpus 0.001326132
allel corpus 0.001323975
corpus sents 0.001322178
different nist 0.001311259
extraction algorithm 0.001279755
other sentences 0.0012683809999999998
bilingual lan 0.00121285
additional features 0.001206419
new sentences 0.001193257
test set 0.001188503
boundary words 0.001188035
words avg 0.0011764380000000001
english machine 0.001170813
english srl 0.001144234
same information 0.001136095
generative models 0.001115595
parallel sen 0.001109877
parallel cor 0.001092741
rule set 0.0010469350000000001
distribution 0.00103172
second problem 0.0010314249999999999
language 0.00102612
sentence 0.00102368
corpus 0.00101392
nist test 0.001009448
assert english 0.00100798
alignment 9.90003E-4
training 9.89157E-4
shared task 9.87371E-4
line models 9.81448E-4
guage models 9.79788E-4
