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

Updates to MIC extraction template #504

Draft
wants to merge 5 commits into
base: main
Choose a base branch
from
Draft

Updates to MIC extraction template #504

wants to merge 5 commits into from

Conversation

caufieldjh
Copy link
Member

No description provided.

@caufieldjh
Copy link
Member Author

Reference extraction isn't working as expected - it appears to treat the refs as a numerical list rather than actually extracting from text, so if one is 20, the next is 21, and so on.

@caufieldjh
Copy link
Member Author

Thinking that reference extraction may need a helper function, to work like so:

  1. Define expected citation format (e.g., inline with parens plus comma or dash)
  2. Given full input text + ref, get coordinates of all inline citations (no LLM)
  3. Link inline citations to reflist (no LLM)
  4. Do extraction with LLM and get coords of all inline citations, but do not retain numbers of citations
  5. Use coords from step 2 to map refs from step 3 to results of step 4

@caufieldjh
Copy link
Member Author

See also monarch-initiative/mic-ingest#5

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

Successfully merging this pull request may close these issues.

1 participant