causaltext / causal-text-papers Goto Github PK

Dear all,

thanks for this awesome repo. I have not seen (maybe I have missed it) any work on learning a causal graph from text where the input would be some text and the output to be predicted (i.e., the labels) would be a corresponding causal graph.
A very simple example would be:

• input: "Ada hits the ball. The ball breaks the window."
• output: (kick the ball) ---> (window breaks)

Are you aware of such kind of work?

Best regards,

Julien

The link to the topic "Learning Representations for Counterfactual Inference" in the README.md file is currently broken. The original link no longer works.

I suggest updating the link in the README.md file to the following arXiv URL: https://arxiv.org/pdf/1605.03661. This link points to the PDF file containing the topic "Learning Representations for Counterfactual Inference."