C02-1097 shows the process of a automatic selective sampling method . The upper side shows
C02-1097 vector is indexed for ` automatic selective sampling ' . In the test phase , contextual
C02-1097 noise is removed using a automatic selective sampling . A automatic selective sampling
C02-1097 negative effects , we use a automatic selective sampling method using cosine similarity
C02-1097 2.5 ) . Then , the ` automatic selective sampling ' module retrieves top-N training
C02-1097 In each test case , a automatic selective sampling method retrieves N relevant training
C02-1097 that will be called " automatic selective sampling " . This automatization is based
C02-1097 automatized hybrid version of selective sampling that will be called " automatic
C02-1097 training samples . The ` automatic selective sampling ' method makes it possible to
C02-1097 without local density and automatic selective sampling . We showed that our method is
J98-4002 formalize and map the concept of selective sampling into example-based approaches
E06-3009 . Only with techniques such as selective sampling and semi-supervised learning
C02-1097 This also shows that automatic selective sampling of training samples in each test
J98-4002 enhances the database . Note that the selective sampling procedure gives us an optimally
J98-4002 should be taken into account during selective sampling . Figure 11 , which uses the
C02-1097 words in test data . 2 ) Automatic selective sampling of training vectors in each test
C02-1097 without local density and automatic selective sampling . 4 . Conclusion This paper reported
C02-1097 vectors for each sense . A automatic selective sampling method was used to construct
C02-1097 selective sampling . A automatic selective sampling method use information retrieval
J98-4000 Model of Intentional Structure Selective Sampling for Example-based Word Sense
hide detail