1 code implementation • 13 May 2023 • Wenjie Xu, Ben Liu, Miao Peng, Xu Jia, Min Peng
We train our model with a masking strategy to convert TKGC task into a masked token prediction task, which can leverage the semantic information in pre-trained language models.
1 code implementation • 10 Oct 2022 • Miao Peng, Ben Liu, Qianqian Xie, Wenjie Xu, Hua Wang, Min Peng
Specifically, we first exploit network schema as the prior constraint to sample negatives and pre-train our model by employing a multi-level contrastive learning method to yield both prior schema and contextual information.