Skip to content
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

bad disambiguation Mundotêxtil -> Ontotext #1

Open
VladimirAlexiev opened this issue Aug 10, 2022 · 1 comment
Open

bad disambiguation Mundotêxtil -> Ontotext #1

VladimirAlexiev opened this issue Aug 10, 2022 · 1 comment

Comments

@VladimirAlexiev
Copy link

Mundotêxtil -> Ontotext: How did this happen?
https://api.openalex.org/works?filter=institutions.id:I46831270

{
  author_position: "middle",
  author: {
    id: "https://openalex.org/A4284117137",
    display_name: "José Lima",
    orcid: null
  },
  institutions: [
    {
      id: "https://openalex.org/I46831270",
      display_name: "Ontotext",
      ror: "https://ror.org/048zn2n32",
      country_code: "BG",
      type: "company"
    }
  ],
  raw_affiliation_string: "Mundotêxtil – Indústrias Têxteis"
},
@jpbarrett13
Copy link
Collaborator

While this is definitely a bad parsing of the affiliation string, our performance on strings in languages other than English is definitely not as good. It's something I hope will be improved in the next version we release in the coming months. Since this is a model based approach, sometimes it can get confused with similar strings (here it is the wordpiece "text"), especially if it is an institution that may not have many samples in the training data.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants