function words 0.001506025
learning system 0.001342479
target language 0.001312121
global word 0.0012877700000000001
word frequency 0.001243606
similarity measure 0.001241975
such data 0.001229417
different learning 0.001226192
class words 0.0012249980000000001
source language 0.0011931910000000001
different selection 0.001167085
input sentence 0.001163596
formal language 0.0011497640000000002
similarity values 0.0011337839999999999
natural language 0.001131482
lemmatized words 0.001127604
test set 0.001120884
language analysis 0.001119676
language related 0.001108272
classification model 0.001096075
programming language 0.0010903100000000002
mal language 0.0010605900000000001
learning examples 0.0010584449999999999
ral language 0.001055142
ural language 0.001050294
textual similarity 0.001049216
assistant system 0.0010457959999999999
bleu similarity 0.001035373
similarity threshold 0.001008428
learning methods 0.001001709
sentence structure 0.001001121
similarity measures 9.95217E-4
baseline system 9.92638E-4
first approach 9.88759E-4
textual data 9.79617E-4
developed system 9.6287E-4
same information 9.60291E-4
learning work 9.49098E-4
learning utterance 9.48813E-4
small set 9.45687E-4
jaccard similarity 9.38644E-4
words 9.32582E-4
function names 9.19172E-4
absolute similarity 9.184569999999999E-4
information retrieval 9.07216E-4
suitable similarity 9.071039999999999E-4
learning process 8.895039999999999E-4
first utterance 8.87368E-4
data collection 8.84389E-4
several methods 8.8426E-4
knowledge set 8.830279999999999E-4
contextual information 8.694270000000001E-4
several utterances 8.65558E-4
model 8.64069E-4
whole set 8.57551E-4
bleu measure 8.563920000000001E-4
language 8.56279E-4
good response 8.4472E-4
annotated data 8.418880000000001E-4
human computer 8.41147E-4
wanted information 8.4061E-4
ing methods 8.36357E-4
initial corpus 8.33795E-4
supervised learning 8.28463E-4
first step 8.100480000000001E-4
useful learning 8.05835E-4
first choice 8.05323E-4
lexical tokens 8.04346E-4
simple approach 7.96742E-4
continuous learning 7.86746E-4
human readers 7.803280000000001E-4
text mining 7.74772E-4
teractive learning 7.68789E-4
system 7.6744E-4
user satisfaction 7.632E-4
user experience 7.606E-4
user sollicitation 7.606E-4
sentence 7.56479E-4
first section 7.53781E-4
formal target 7.493269999999999E-4
mapping methods 7.44244E-4
ilarity measure 7.43627E-4
candidate utterances 7.300189999999999E-4
measure outper 7.29419E-4
measure tfidf 7.27124E-4
measure permits 7.27124E-4
several commands 7.14957E-4
selection strate 7.12051E-4
similarity 7.10478E-4
first pass 7.091210000000001E-4
utterance level 7.04932E-4
single utterance 6.94677E-4
corpus constitution 6.92299E-4
several strategies 6.91888E-4
ambiguous examples 6.89261E-4
third examples 6.847120000000001E-4
tiny corpus 6.83392E-4
poor performance 6.82726E-4
card examples 6.80927E-4
same time 6.75311E-4
