word sense 0.00653551
sense word 0.00653551
training sense 0.00522824
same sense 0.004730199
sense vector 0.004697507
sense disambiguation 0.004659273
possible sense 0.004475333
sense vectors 0.004450888
sense clusters 0.004441665
sense cluster 0.004430519
sense granularity 0.00442459
only sense 0.004397616
sense distinctions 0.004387315
quent sense 0.004386233
sense classifica 0.004383153
sense tagged 0.004380174
terpret sense 0.004379005
twa sense 0.004379005
nancial sense 0.004379005
sense gran 0.004379005
sense 0.00412459
word senses 0.003388408
chinese word 0.003322394
word translation 0.00325339
english word 0.003089378
corpora word 0.003026629
same word 0.003016529
ambiguous word 0.002809724
word space 0.002766958
word portion 0.002709278
word order 0.002699108
word recogniser 0.002664993
word segmenter 0.002664993
chinese words 0.002447004
english words 0.002213988
context words 0.002190932
training data 0.00215299
other words 0.002056497
similar words 0.002010588
training corpus 0.001925422
wsd system 0.00182366
content words 0.001813819
polysemous words 0.0017937019999999999
chinese translation 0.001753944
english topic 0.0017451379999999998
chinese corpus 0.001733246
chinese text 0.001715125
different senses 0.0016944430000000001
test training 0.001673815
wsd algorithm 0.001657501
vector model 0.001620657
test data 0.0016195049999999998
wsd task 0.001601308
target topic 0.001574709
standard wsd 0.0015405290000000001
words 0.00153553
wsd datasets 0.001533834
chinese corpora 0.001527183
wsd algorithms 0.0015245670000000001
english translation 0.001520928
wsd experiments 0.0014800920000000001
good training 0.0014598570000000002
semantic similarity 0.0014547269999999998
training sets 0.001439699
wsd algo 0.001401478
training stage 0.001398989
sufficient training 0.0013855120000000002
topic signatures 0.001380667
ity topic 0.001372435
training phase 0.0013684020000000001
topic sig 0.001365893
annotated data 0.001364939
quality data 0.0013424609999999999
topic signature 0.001338692
topic signa 0.00132346
glish topic 0.001321615
spanish topic 0.001321615
french topic 0.001321615
tagged data 0.0013049239999999998
data collection 0.001303599
chinese translations 0.001277778
chinese document 0.001274028
machine translation 0.001248944
translation lexicon 0.001240137
bilingual text 0.0012394889999999999
context vector 0.001228319
chinese string 0.001207432
large set 0.00119903
ldc chinese 0.001198796
translation software 0.001196892
engine chinese 0.001187696
same test 0.001175774
chinese segmentation 0.001172443
chinese synonyms 0.001171062
chinese gigaword 0.001169953
chinese monolin 0.001166112
national corpus 0.0011539200000000001
daily corpus 0.001130176
different approach 0.001129234
other knowledge 0.001113238
