Table 2: 
Performance using Macro-F1% on automatically created Wikipedia test set; models with the symbol † are significantly (p < 0.05) different from the best system in each task using the approximate randomization test (Noreen, 1989).
SystemsSentencesDocuments
en zh en zh 
Major 2.81† 5.99† 3.81† 4.41† 
L-LDA 38.52† 37.09† 63.10† 58.74† 
HierNet 30.01† 37.26† 75.00 68.56† 
MilNet 37.12† 44.37† 50.90† 69.45† 
 
DetNet1ℋ 47.93† 51.31† 74.91 72.85 
DetNet2ℋ 47.89† 52.50† 75.47 71.96† 
DetNet* 54.37 55.88 76.48 74.24 
SystemsSentencesDocuments
en zh en zh 
Major 2.81† 5.99† 3.81† 4.41† 
L-LDA 38.52† 37.09† 63.10† 58.74† 
HierNet 30.01† 37.26† 75.00 68.56† 
MilNet 37.12† 44.37† 50.90† 69.45† 
 
DetNet1ℋ 47.93† 51.31† 74.91 72.85 
DetNet2ℋ 47.89† 52.50† 75.47 71.96† 
DetNet* 54.37 55.88 76.48 74.24 
View Large
Close Modal
This Feature Is Available To Subscribers Only

or Create an Account

Close Modal
Close Modal
This site uses cookies. By continuing to use our website, you are agreeing to our privacy policy. No content on this site may be used to train artificial intelligence systems without permission in writing from the MIT Press.
Accept