Skip to Main Content
Table 14 
Correlation scores obtained with LessLex on different subsets of data obtained by varying standard deviation in human ratings. The reported figures show higher correlation when testing on the most reliable (with smaller standard deviation) portions of the data set. To interpret the standard deviation values, we recall that the original ratings collected in the SCWS data set were expressed in the range [0.0,10.0].
σc-rank-sim (r)rank-sim (r)nof-items
≤ 0.5 0.83 0.82 39 
≤ 1.0 0.85 0.86 82 
≤ 1.5 0.85 0.85 165 
≤ 2.0 0.82 0.84 285 
≤ 2.5 0.68 0.83 518 
≤ 3.0 0.68 0.79 903 
≤ 3.5 0.67 0.75 1, 429 
≤ 4.0 0.64 0.71 1, 822 
<5.0 0.63 0.69 2, 003 
σc-rank-sim (r)rank-sim (r)nof-items
≤ 0.5 0.83 0.82 39 
≤ 1.0 0.85 0.86 82 
≤ 1.5 0.85 0.85 165 
≤ 2.0 0.82 0.84 285 
≤ 2.5 0.68 0.83 518 
≤ 3.0 0.68 0.79 903 
≤ 3.5 0.67 0.75 1, 429 
≤ 4.0 0.64 0.71 1, 822 
<5.0 0.63 0.69 2, 003 
Close Modal

or Create an Account

Close Modal
Close Modal