how to interpret this result

[kvjunior]

please I would like to know how to interpret this result

[yzhangee]

Please refer to the README file:
The first 4 values (a,b,c,d) represent h_1 * r_1 * t_a + h_2 * r_2 * t_b + h_3 * r_3 * t_c + h_4 * r_4 * t_d.
For the others, every 4 values represent one block: index of r, index of h, index of t, sign s.

For example, the scoring function of Analogy is formed as [0,1,2,2,3,2,3,-1,2,3,3,1]:
f(h,r,t) = h_1r_1t_1 + h_2r_2t_2 + h_3r_3t_3 + h_4r_4t_3 + h_4r_3t_4*(-1) + h_3r_4t_4*(1).

You can understand together with the get_hr() function in models.py

[kvjunior]

Thanks a lot Le mar. 27 oct. 2020 à 19:27, ZHANG YONGQI <notifications@github.com> a écrit :

…

Please refer to the README file: The first 4 values (a,b,c,d) represent h_1 * r_1 * t_a + h_2 * r_2 * t_b + h_3 * r_3 * t_c + h_4 * r_4 * t_d. For the others, every 4 values represent one block: index of r, index of h, index of t, sign s. For example, the scoring function of Analogy is formed as [0,1,2,2,3,2,3,-1,2,3,3,1]: f(h,r,t) = h_1*r_1*t_1 + h_2*r_2*t_2 + h_3*r_3*t_3 + h_4*r_4*t_3 + h_4 *r_3*t_4*(-1) + h_3*r_4*t_4*(1). You can understand together with the get_hr() function in models.py — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub <#2 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AOK2P7N6HCYENEGAI4CGQ7DSM2VDJANCNFSM4TAVMORQ> .

-- cordially, Victor KOMBOU +8615528443304 (Wathsapp Wechat "kvjunior")

[kvjunior]

in fact my concern is related to the interpretation of the results that I obtained after testing your code. I would like to know how to interpret this Le mer. 28 oct. 2020 à 00:39, Quanming Yao <notifications@github.com> a écrit :

…

Closed #2 <#2>. — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub <#2 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AOK2P7ON7GNEWUJ4RHKEQWLSM3ZTDANCNFSM4TAVMORQ> .

-- cordially, Victor KOMBOU +8615528443304 (Wathsapp Wechat "kvjunior")

[jpainam]

@yzhangee @quanmingyao @skeletondyh Hi, I'm having the same difficulty.

1. After training with bash run.sh, I get the following results saved in WN18_perf.txt file as

1 2 0 3 		best_performance: 0.7187	0.8277		0.7131	0.8213
3 0 1 2 		best_performance: 0.7884	0.8459		0.7877	0.8470
1 0 2 3 		best_performance: 0.9488	0.9533		0.9488	0.9548
2 3 0 1 		best_performance: 0.9486	0.9541		0.9490	0.9565
0 1 2 3 		best_performance: 0.8099	0.9466		0.8128	0.9503
2 3 0 1 2 3 3 1 0 2 2 1 		best_performance: 0.9482	0.9534		0.9483	0.9546
2 3 0 1 2 3 3 -1 2 2 2 1 		best_performance: 0.9454	0.9536		0.9450	0.9542
etc..

I would like to know what these numbers (e.g. 0.9454 0.9536 0.9450 0.9542) represent? Do they represent the hit? I your paper, you reported the MRR, H@1 and the H@10. But here, i see four numbers for each function.

2. It is possible to only test the model using the obtained scoring function f(h,r,t) for evaluation.

Thanks

[yzhangee]

The output string has been optimized and the re-evaluation code is released.