search

wenhuchen / LogicNLG

The data and code for ACL2020 paper "Logical Natural Language Generation from Open-Domain Tables"
MIT License
166 stars 22 forks source link

Evaluate your model on my own table data #7

Closed vnik18 closed 3 years ago

vnik18 commented 3 years ago

Hello,

Thank you for sharing your great work and code. I would like to evaluate your trained models on my own test set of tables. According to the format of your file test_lm.json, I need 

[
      sent1,
      linked columns1,
      table title,
      template1
    ]

I have table title available. Linked columns1 and template1 are generated by entity linking. Can you please tell me how to generate sent1? Is there any script for this in your code repository? Thank you.

wenhuchen commented 3 years ago

If I understand your question clearly, you are asking about how the text is generated, right? In my dataset, it's written by humans through the Amazon Mechnical Turker Platform.

vnik18 commented 3 years ago

Yes, I am asking how the text in the sent1 field of your file test_lm.json is generated. Thank you.