-
Notifications
You must be signed in to change notification settings - Fork 8
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
A question about the chart in the paper #2
Comments
Sorry, I cannot see your que.png, but I guess it may be the Figure 2: Processing step of different RE paradigms. in the paper. {WWE, country, us} is only an example, meaning you extract the relations and use 'country' to extract the triplet fact. You later recognize the head entities (here WWE and others), and you loop through each head entity to extract the corresponding fact. When looping to WWE, you extract the facts corresponding to this entity. WWE may act as the subject, and the corresponding tails might be more than one. In the paper, it is merely used as an example. |
Thank you for your explanation. I understand now. In addition, I found that the server of the deployment platform you wrote in the paper cannot be opened, could you please deal with it? thank you. |
Sorry about that, there are some problems with the machine, I am trying to migrate the service to another machine. Best~ |
I understand the first three ways to extract triples, what does the fourth diagram you proposed mean? What do the dotted and solid lines represent, and is the last one just extracted {WWE,country,us}?
The text was updated successfully, but these errors were encountered: