Skip to Main Content
Table 1: 
Results summary, cross-lingual parsing, K = 100. We report average (Av.) and median (Md.) UAS (across languages) of each model with MOM inference (M) and with an oracle that chooses the best tree out of the K-list produced by the model (O). The # Cor. columns report the number of corpora for which the model is the best scoring one (in case two models perform best on the same language, it counts for both). For 1-best and KG (1-best), both MOM (M) and Oracle (O) refer to the single tree produced by the model.
Method Av. UAS (M) Md. UAS (M) Av. UAS (O) Md. UAS (O) # Cor. (M) # Cor. (O) 
1-best 66.4 70.2 66.4 70.2 
K-best 58.5 62.8 74.8 77.1 
AFN 66.6 70.6 73.4 76.9 
MFN 62.6 65.2 77.1 78.7 14 
ALN 66.9 70.9 76.9 80.4 
MLN 67.4 71.4 80.3 83.4 39 58 
KG 66.6 69.9 66.6 69.9 26 
Method Av. UAS (M) Md. UAS (M) Av. UAS (O) Md. UAS (O) # Cor. (M) # Cor. (O) 
1-best 66.4 70.2 66.4 70.2 
K-best 58.5 62.8 74.8 77.1 
AFN 66.6 70.6 73.4 76.9 
MFN 62.6 65.2 77.1 78.7 14 
ALN 66.9 70.9 76.9 80.4 
MLN 67.4 71.4 80.3 83.4 39 58 
KG 66.6 69.9 66.6 69.9 26 
Close Modal

or Create an Account

Close Modal
Close Modal