Closed iamlockelightning closed 5 years ago
The results of IPTransE on DBP15K were produced using my own implementation because there was no official code at that time. I would suggest you to try more parameter settings, such as the similarity threshold.
Thank you for your reply!! And I saw the e-mail just now. Yes, I found that the iteration predicted many false pairs, but it was hard to control the threshold dynamically. I will try on. Thanks again!
Hi, Zequn. I try to use https://github.com/thunlp/IEAJKE(IPTransE) to reproduce the results of IPTransE on DBP15Kzh-en. But the results are so much bad than what reported in your paper BootEA(My results are Hit@1: 0.1941, Hit@10: 0.4685, MRR: 0.2833). I just changed the data format of the DBP15Kzh-en to what IPTransE needs. No parameters modified. Would you like to share some advice on it? (Or kindly would you like to share the code/input_dataset that you use?) Thanks!