topic clustering 0.002305749
important topic 0.002243656
main topic 0.00223349
document keyphrases 0.0022234100000000003
topic cluster 0.002101751
topic clusters 0.002071271
topic community 0.002010089
topic change 0.002008362
freebase topic 0.002001734
topic sprint 0.0019914
topic correlation 0.0019914
probable topic 0.0019914
topic 0.00175867
candidate keyphrases 0.001725297
candidate keyphrase 0.0016739609999999999
keyphrase extraction 0.001664208
document frequency 0.00164973
document index 0.001642457
such features 0.0015531870000000001
document length 0.00151662
inverse document 0.0014865520000000001
other words 0.0014826000000000002
high term 0.001473202
input document 0.001466831
important word 0.00145751
unseen document 0.001457353
word olympic 0.001452264
candidate words 0.0014361
many keyphrase 0.00143003
same word 0.001401619
gold keyphrases 0.001389775
supervised keyphrase 0.001378289
automatic keyphrase 0.001374285
correct keyphrases 0.001350607
gold keyphrase 0.001338439
ranking method 0.001319537
candidate phrase 0.001306602
syntactic features 0.001305959
other documents 0.001290577
other feature 0.001285275
human evaluation 0.001254987
word sequence 0.001253133
fact keyphrases 0.001253
equivalent keyphrases 0.0012473150000000001
way keyphrase 0.001246341
word list 0.001243594
tract keyphrases 0.001243472
infrequent keyphrases 0.001238085
term fre 0.0012311700000000002
document 0.00122228
term extractor 0.001220579
keyphrase indepen 0.001217275
extraction system 0.001215693
stop word 0.001214253
large text 0.001207165
structural features 0.0012067480000000001
mutual information 0.001201396
important words 0.001196919
art keyphrase 0.001196305
language model 0.001193916
keyphrase extractors 0.00118855
infrequent keyphrase 0.001186749
keyphrase extrac 0.001185756
keyphrase extractor 0.001184466
keyphrase incor 0.00118117
section information 0.001178172
structural information 0.001173072
coherence features 0.001171237
statistical features 0.001168844
text collection 0.001162138
distributional features 0.001161829
ranking approach 0.0011576429999999999
candidate keywords 0.001152897
candidate frequency 0.001151617
sophisticated features 0.00113503
information retrieval 0.001122896
text summarization 0.001120805
extraction systems 0.001113543
automatic evaluation 0.001107965
tistical information 0.001101652
other candidates 0.001098894
important topics 0.001095314
main topics 0.001085148
evaluation error 0.001080796
other node 0.0010751670000000001
text sum 0.0010697039999999999
other types 0.0010664860000000002
semantic relatedness 0.001064482
evaluation errors 0.001062706
wikipedia article 0.001059753
clustering approach 0.00105715
guage model 0.001045305
informal text 0.001044417
candidate ben 0.0010404589999999999
different learning 0.001029367
other variations 0.0010218990000000002
evaluation metrics 0.001018173
conversational text 0.001015632
final score 0.00101537
feature values 0.001012568
