Difference between revisions of "2006:Symbolic Melodic Similarity Results"
(→Calculating Summary Measures) |
(→Calculating Summary Measures) |
||
| Line 23: | Line 23: | ||
'''Average Precision (non-interpolated)''' = needs definition <br /> | '''Average Precision (non-interpolated)''' = needs definition <br /> | ||
'''Precision at N Documents''' = needs defining <br /> | '''Precision at N Documents''' = needs defining <br /> | ||
| − | '''Fine''' = Sum of fine-grained human similarity decisions (0-10) <br /> | + | '''Fine''' = Sum of fine-grained human similarity decisions (0-10). <br /> |
| − | '''PSum''' = Sum of human similarity decisions: NS=0, SS=1, VS=2. <br /> | + | '''PSum''' = Sum of human broad similarity decisions: NS=0, SS=1, VS=2. <br /> |
'''WCsum''' = 'World Cup' scoring: NS=0, SS=1, VS=3 (rewards Very Similar). <br /> | '''WCsum''' = 'World Cup' scoring: NS=0, SS=1, VS=3 (rewards Very Similar). <br /> | ||
| − | '''SDsum''' = 'Stephen Downie' scoring: NS=0, SS=1, VS=4 | + | '''SDsum''' = 'Stephen Downie' scoring: NS=0, SS=1, VS=4 (strongly rewards Very Similar. <br /> |
| − | '''Greater0''' = NS=0, SS=1, VS=1 (binary relevance judgement)<br /> | + | '''Greater0''' = NS=0, SS=1, VS=1 (binary relevance judgement).<br /> |
| − | '''Greater1''' = NS=0, SS=0, VS=1 (binary relevance using only Very Similar)<br /> | + | '''Greater1''' = NS=0, SS=0, VS=1 (binary relevance judgement using only Very Similar).<br /> |
==Overall Summary Results== | ==Overall Summary Results== | ||
Revision as of 16:04, 25 September 2006
Contents
Introduction
These are the results for the 2006 running of the Symbolic Melodic Similarity task set. For background information about this task set please refer to the Symbolic Melodic Similarity page.
General Legend
Team ID
Prefix R = RISM collection, K = Karaoke collection, M = Polyphonic collection
FH = Pascal Ferraro and Pierre Hanna
NM = Kjell Lemström, Niko Mikkilä, Veli Mäkinen and Esko Ukkonen
RT = Rainer Typke
KF = Klaus Frieler
AU = Alexandra Uitdenbogerd
Broad Categories
NS = Not Similar
SS = Somewhat Similar
VS = Very Similar
Calculating Summary Measures
Average Dynamic Recall = needs definition
Normalize Recall at Group Boundaries = needs defining
Average Precision (non-interpolated) = needs definition
Precision at N Documents = needs defining
Fine = Sum of fine-grained human similarity decisions (0-10).
PSum = Sum of human broad similarity decisions: NS=0, SS=1, VS=2.
WCsum = 'World Cup' scoring: NS=0, SS=1, VS=3 (rewards Very Similar).
SDsum = 'Stephen Downie' scoring: NS=0, SS=1, VS=4 (strongly rewards Very Similar.
Greater0 = NS=0, SS=1, VS=1 (binary relevance judgement).
Greater1 = NS=0, SS=0, VS=1 (binary relevance judgement using only Very Similar).
Overall Summary Results
RISM overall summary
file /nema-raid/www/mirex/results/sms06_rism_sum.csv not found
Karaoke overall summary
file /nema-raid/www/mirex/results/sms06_karaoke_sum.csv not found
Mixed Polyphonic overall summary
file /nema-raid/www/mirex/results/sms06_mixed_sum.csv not found
Task I: RISM Collection Summary Results
file /nema-raid/www/mirex/results/sms06_rism_results2.csv not found
Task IIa: Karaoke Collection Summary Results
file /nema-raid/www/mirex/results/sms06_kar_results2.csv not found
Task IIb: Mixed Polyphonic Collection Summary Results
file /nema-raid/www/mirex/results/sms06_mix_results2.csv not found
Raw Scores
The raw data derived from the Evalutron 6000 human evaluations are located on the Symbolic Melodic Similarity Raw Data page.
