question about the kg2text task

Question

question about the kg2text task

jiangliqin opened this issue 3 years ago · 13 comments

Hi,
firstly, thanks a lot for your work.
I have a question about the kg2text task in the project, no example and information about the kg2text, but i read your code, and found the kg dataset processor.
Could you please take some dataset and the corresponding model for example to further explain the kg2text details?

Answer 1 · 2021-12-22T03:32:24.000Z

Thanks for your attention.
The KG2text task is still under test, and we will release detailed instruction in the next version.

Answer 2 · 2021-12-23T03:30:46.000Z

I'm looking forward your KG2text task research, and what's the roughly time about the next version?

Answer 3 · 2021-12-23T06:11:28.000Z

It may be until February or March. We are working on papers recently.
We only support the GraphWriter (Text Generation from Knowledge Graphs with Graph Transformers) now, if you need it, we can provide instructions.

Answer 4 · 2021-12-23T06:34:23.000Z

ok,I need it,please give some instructions.
Actually it seems that the GraphWriter performance is not pretty good, do u know the better KG2text model to suggest me?I will learn from it,thanks!

Answer 5 · 2021-12-23T06:37:43.000Z

Investigating Pretrained Language Models for Graph-to-Text Generation
Few-shot Knowledge Graph-to-Text Generation with Pretrained Language Models
KGPT Knowledge-Grounded Pre-Training for Data-to-Text Generation

Some kg2text papers, you can treat them as strong baselines. The intruction of GraphWriter will be released soon.

Answer 6 · 2021-12-23T07:07:56.000Z

awesome!Thanks again for your sharing!

Answer 7 · 2021-12-24T08:25:18.000Z

Hi,StevenTang, do you know the Chinese-related PLM for kg2text paper?Using the method of paper,I should prepare the large amount Chinese corpus to pretrain the model which is burdensome.

Answer 8 · 2021-12-25T01:45:08.000Z

Sorry I know little about this.

Answer 9 · 2021-12-26T03:07:05.000Z

We have upload the Agenda dataset in Baidu WangPan.
You can pull the lastest repository and run the following command:
python run_textbox.py --model=Kb2Text --dataset=Agenda

Answer 10 · 2021-12-27T05:48:43.000Z

get it, thanks for syncing it to me in time

Answer 11 · 2022-01-11T01:20:48.000Z

similar to kg2text, the table2text task is also needed, how long will you release the table2text details?

Answer 12 · 2022-01-11T01:48:48.000Z

The table2text model is a little outdated, and may not be a good choice as a baseline. You can use PLMs with linearized table.

Answer 13 · 2022-01-11T02:26:49.000Z

fine, my weChat is “hashenbb”, could you add my weChat for text generation discussion?