• Load from URL
  • Load from currently selected Zotero item
  • Use EXparser
  • Use AnyStyle
  • Train currently selected model
  • Evaluate currently selected model
  • Run OCR on PDF
  • Extract text from PDF
  • Extract references from PDF
  • Auto-segmentation
  • Switch firstname & lastname
  • Preview citation data
  • Export references to Zotero item
img mpilhlt
   

        
  • Markup selection as reference
  • Markup whole line(s) as reference
  • Ignore
  • Reference
  • Meta
  • Page Number
  • Text
  • Title
  • Author
  • Abstract
  • Author(s)
  • Date
  • Title
  • Editor(s)
  • Location
  • Publisher
  • Journal
  • Container
  • Collection
  • Volume
  • Pages
  • DOI
  • ISBN
  • URL
  • Surname
  • Given‑names
  • Year
  • Title
  • Editor(s)
  • Publisher
  • Source
  • Volume
  • Issue
  • First page
  • Last Page
  • Identifier
  • URL
  • Ignore
  • Linebreak
  • Remove Tag
  • Remove all tags inside selection
  • Remove all tags in line(s)

Citation extraction and segmentation annotation for AnyStyle and EXparser

This web application is meant to help the annotation of training documents for machine learning-based reference extraction.

It supports the annotation formats of AnyStyle and of EXparser.

See the Dcoumentation on GitHub

Citation data preview