MIT Press

Table 2:

Cross-lingual parsing results as a function of K, the size of the K list for the K-best and MLN parsers. A-U and M-U refer to average and median UAS across languages, respectively. #-C refers to the number of corpora for which the model is the best scoring one. (M) refers to MOM inference, while (O) refers to oracle selection of the best tree from the list. A-U-T and M-U-T refer to the average and median number of unique trees in the list, respectively. As noted above, the K-best model cannot generate K trees for all sentences.

Method	A-U (M)	M-U (M)	A-U (O)	M-U (O)	#-C (M)	#-C (O)	A-U-T	M-U-T
10-best	63.1	67.4	72.7	75.5	3	5	9.8	10
MLN-10	66.6	70.5	75.1	78.1	69	67	6.86	8

200-best	57.2	60.7	75.1	77.3	0	1	126.1	130
MLN-200	67.6	71.6	83.2	85.8	72	71	92.7	96

Method	A-U (M)	M-U (M)	A-U (O)	M-U (O)	#-C (M)	#-C (O)	A-U-T	M-U-T
10-best	63.1	67.4	72.7	75.5	3	5	9.8	10
MLN-10	66.6	70.5	75.1	78.1	69	67	6.86	8

200-best	57.2	60.7	75.1	77.3	0	1	126.1	130
MLN-200	67.6	71.6	83.2	85.8	72	71	92.7	96

View Large

This Feature Is Available To Subscribers Only