Table 7. Experimental results of comparing systems on the diverse data sets for finding similar questions.

Models	Cong et al.		Twitter
	AP	p@1	AP	p@1
BC	0.517	0.520	0.551	0.570
BCF	0.525	0.532	0.559	0.570
upBC	0.533	0.544	0.577	0.585
STM	0.554	0.560	0.593	0.600
LDAC	0.598	0.615	0.608	0.620
LDACF	†	‡	†	‡

^{† and ‡}indicates the results of our proposed methods are statistical significance over the four baseline methods (within 0.95 confidence interval using the -test). The results of our proposed approach are in bold.