Calculation of Sentence Semantic Similarity Based on Syntactic Structure

Table 3

Part of experimental data of sentence similarity computation.

Test sentences	Method 1	Method 2	Method 3
C1: The capital of Beijing is beautiful.; (Chinese text: Shou du Beijing hen mei li.); C2: Our capital is Bejing.; (Chinese text: Wo men de shou du shi Beijing.)	0.5714	0.5000	0.1276
C3: He knitted a long scarf.; (Chinese text: Ta da le yi tiao chang chang de wei jin.); C4: He held up a beautiful umbrella.; (Chinese text: Ta da le yi ba piao liang de yu san.)	0.5000	0.6625	0.4274
C5: He went to work today.; (Chinese text: Ta jin tian shang ban le.); C6: He didn’t go to work yesterday.; (Chinese text: Ta zuo tian mei shang ban.)	0.5714	0.5500	−0.7720
C7: I enjoy comfortable life.; (Chinese text: Wo xi huan shu shi de sheng huo.); C8: Hands up if you agree.; (Chinese text: Tong yi de ren qing ju shou.)	0.0000	0.0000	0.0770
C9: I love to eat apples.; (Chinese text: Wo ai chi ping guo.); C10: The fruit I like are apples.; (Chinese text: Wo xi huan de shui guo shi ping guo.)	0.4444	0.3600	0.1928
C11: How is she recently?; (Chinese text: Ta zui jin hao ma?); C12: She is very fine recently.; (Chinese text: Ta zui jin hen hao.)	1.0000	0.7750	0.1000
C13: He pushed his younger brother over.; (Chinese text: Ta ba di di tui dao le.); C14: His younger brother was pushed over by him.; (Chinese text: Di di bei ta tui dao le.)	0.7500	0.5400	1.0000