kgt5 icon indicating copy to clipboard operation
kgt5 copied to clipboard

Sequence-to-Sequence Knowledge Graph Completion and Question Answering (KGT5)

Results 16 kgt5 issues
Sort by recently updated
recently updated
newest added

Hi Apoorv, Thanks for the great work! I can't download the KGC and KGQA datasets from the connection you provided (https://storage.googleapis.com/t5-kgc-colab/data/data.zip, https://storage.googleapis.com/t5-kgc-colab/data/data_kgqa.zip). However, other datasets can be downloaded in https://storage.googleapis.com....

Hello, may I ask if the explanation for kgqa can be updated

Hello, this work is terrific, and I am happy to find your work. But I have some questions. Could I use your model for Chinese Triples data? If it is...

Hi, Is there a checkpoint that I can use directly?

thanks for your genius approach!while reproducing the result of link-prediction, I wondering where does the model calculate hit!@1 and hit@10 on Wikidata5M? I only found loss and acc。Looking forward to...

Hello,apoorv! @apoorvumang Thank you for your excellent work!.You provide one-to-one mapping between the entities/relationships of Wikidata5m and their text representations in the code, but there is no mapping of other...

In the paper you explicitly mentioned that you trained a BPE tokenizer for your experiments: ![image](https://user-images.githubusercontent.com/43718473/231147502-69eb29ae-9fbb-491e-b119-4a23cf9c01ee.png) However, in the code of the dataset.py you used [T5TokenizerFast that is based on...

Hi @apoorvumang! In issue #8 you mentioned that to calculate the metrics reported in the paper you used code from ```eval_accelerate.py```. For me, it is still not clear how you...

Nice work. However, I have some questions about the link prediction task on Wikidata5m dataset. With your training code, I train the model for 4M steps, and the Hits@1 accuracy...

Following issue #23 I make this issue in order to track pretrained checkpoints for QA. I hope that authors will add them soon. Thank you again!