Skip to Main Content
Table 5: 

Punctuation vs. dialog act counts for MRDA dataset. Percentage of errors for a given act and punctuation are shown in parentheses (the lower, the better the recognition).

Full stopExcl. markQ. markNone
Backchannel 2120 (18.44 (50.0) 0 (0) 28 (60.7) 
Disruption 115 (93.9) 2 (100.0) 6 (100.0) 2216 (43.1
Floor-grabber 257 (75.5) 0 (0) 0 (0) 1152 (49.7
Question 10 (20.0) 0 (0) 1231 (8.90 (0) 
Statement 9445 (14.5) 79 (8.951 (60.8) 2 (100.0) 
Full stopExcl. markQ. markNone
Backchannel 2120 (18.44 (50.0) 0 (0) 28 (60.7) 
Disruption 115 (93.9) 2 (100.0) 6 (100.0) 2216 (43.1
Floor-grabber 257 (75.5) 0 (0) 0 (0) 1152 (49.7
Question 10 (20.0) 0 (0) 1231 (8.90 (0) 
Statement 9445 (14.5) 79 (8.951 (60.8) 2 (100.0) 
Close Modal

or Create an Account

Close Modal
Close Modal