Table 6: 

Overconfidence Error Results.

DP
BCBNMZNWTCWBAverage
ST-EC-DP (CE) 0.0720 0.0672 0.0757 0.0506 0.0584 0.3064 0.1051 
ST-EC-DP (TS) 0.0753 0.0651 0.0673 0.0421 0.0545 0.3012 0.1009 
ST-EC-DP (LS) 0.0269 0.0186 0.0122 0.0107 0.0289 0.1725 0.0450 
ST-DA-DP (CE) 0.0410 0.0392 0.0414 0.0337 0.0381 0.1098 0.0505 
 
NER 
 BC BN MZ NW TC WB Average 
ST-EC-NER (CE) 0.0111 0.0167 0.0131 0.0146 0.0090 0.0132 0.0130 
ST-EC-NER (TS) 0.0100 0.0172 0.0136 0.0108 0.0087 0.0142 0.0124 
ST-EC-NER (LS) 0.0002 0.0002 0.0001 0.0002 0.0009 0.0010 0.0004 
ST-DA-NER (CE) 0.0090 0.0121 0.0117 0.0122 0.0082 0.0110 0.0107 
 
DP + NER 
 BC BN MZ NW TC WB Average 
MT-AVG (CE) 0.0436 0.0499 0.0473 0.0345 0.0393 0.1681 0.0637 
MT-AVG (TS) 0.0447 0.0468 0.0460 0.0318 0.0396 0.1645 0.0622 
MT-AVG (LS) 0.0040 0.0018 0.0013 0.0012 0.0057 0.0546 0.0114 
MT-AVGDA (CE) 0.0291 0.0287 0.0302 0.0236 0.0257 0.0718 0.0349 
DP
BCBNMZNWTCWBAverage
ST-EC-DP (CE) 0.0720 0.0672 0.0757 0.0506 0.0584 0.3064 0.1051 
ST-EC-DP (TS) 0.0753 0.0651 0.0673 0.0421 0.0545 0.3012 0.1009 
ST-EC-DP (LS) 0.0269 0.0186 0.0122 0.0107 0.0289 0.1725 0.0450 
ST-DA-DP (CE) 0.0410 0.0392 0.0414 0.0337 0.0381 0.1098 0.0505 
 
NER 
 BC BN MZ NW TC WB Average 
ST-EC-NER (CE) 0.0111 0.0167 0.0131 0.0146 0.0090 0.0132 0.0130 
ST-EC-NER (TS) 0.0100 0.0172 0.0136 0.0108 0.0087 0.0142 0.0124 
ST-EC-NER (LS) 0.0002 0.0002 0.0001 0.0002 0.0009 0.0010 0.0004 
ST-DA-NER (CE) 0.0090 0.0121 0.0117 0.0122 0.0082 0.0110 0.0107 
 
DP + NER 
 BC BN MZ NW TC WB Average 
MT-AVG (CE) 0.0436 0.0499 0.0473 0.0345 0.0393 0.1681 0.0637 
MT-AVG (TS) 0.0447 0.0468 0.0460 0.0318 0.0396 0.1645 0.0622 
MT-AVG (LS) 0.0040 0.0018 0.0013 0.0012 0.0057 0.0546 0.0114 
MT-AVGDA (CE) 0.0291 0.0287 0.0302 0.0236 0.0257 0.0718 0.0349 
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