MultiCoNER II: Multilingual Complex Named Entity Recognition

# MultiCoNER II: Multilingual Complex Named Entity Recognition
# Based on SemEval-2023 Task 2 (Fetahu et al., SemEval@ACL 2023)
# Paper: https://aclanthology.org/2023.semeval-1.310/
# Dataset: https://multiconer.github.io/dataset
#
# Task: Fine-grained NER across 12 languages with complex entities
# Annotators identify named entities from a fine-grained taxonomy
# that includes creative works, groups, medical terms, and more.
#
# Key Challenges:
# - Complex entities requiring world knowledge (e.g., song titles)
# - Ambiguous entities that could belong to multiple types
# - Multilingual text with code-switching
# - Low-context short sentences from search queries and social media
#
# Entity Types (6 coarse groups; each spans fine-grained subtypes):
# - Person: Scientist, Artist, Athlete, Politician, Cleric, SportsManager, OtherPER
# - Location: Facility, HumanSettlement, Station, OtherLOC
# - Group: MusicalGRP, PublicCORP, PrivateCORP, AerospaceManufacturer,
#          SportsGRP, CarManufacturer, ORG (companies/institutions)
# - CreativeWork: VisualWork, MusicalWork, WrittenWork, ArtWork, Software
# - Product: Clothing, Vehicle, Food, Drink, OtherPROD
# - Medical: Medication/Vaccine, MedicalProcedure, AnatomicalStructure, Symptom, Disease

annotation_task_name: "MultiCoNER II: Complex Named Entity Recognition"
task_dir: "."

data_files:
  - sample-data.json
item_properties:
  id_key: "id"
  text_key: "text"

output_annotation_dir: "annotation_output/"
output_annotation_format: "json"

annotation_schemes:
  - annotation_type: span
    name: entities
    description: "Highlight all named entities and assign their fine-grained type"
    labels:
      - "Person"
      - "Location"
      - "Group"
      - "CreativeWork"
      - "Product"
      - "Medical"
    label_colors:
      "Person": "#3b82f6"
      "Location": "#22c55e"
      "Group": "#f59e0b"
      "CreativeWork": "#ec4899"
      "Product": "#06b6d4"
      "Medical": "#ef4444"
    tooltips:
      "Person": "People: scientists, artists, athletes, politicians, clerics, sports managers, others (e.g., Albert Einstein, Lamine Yamal)"
      "Location": "Facilities, human settlements, stations, other locations (e.g., Tokyo, Elbphilharmonie, Ohio State Reformatory)"
      "Group": "Musical groups, public/private corporations, sports groups, aerospace/car manufacturers, and other organizations (e.g., Daft Punk, FC Barcelona, Sony, WHO)"
      "CreativeWork": "Visual works, musical works, written works, artworks, software (e.g., The Shawshank Redemption, PlayStation 5 Pro games)"
      "Product": "Clothing, vehicles, food, drink, other products (e.g., iPhone, Boeing 747, Snapdragon 8 Gen 3)"
      "Medical": "Medications/vaccines, medical procedures, anatomical structures, symptoms, diseases (e.g., COVID-19, remdesivir, rVSV-ZEBOV)"
    allow_overlapping: false

html_layout: |
  <div style="margin-bottom: 10px; padding: 8px; background: #f0f4ff; border-radius: 6px;">
    <strong>Language:</strong> {{language}}
  </div>
  <div style="padding: 10px; border: 1px solid #ddd; border-radius: 6px; line-height: 1.8; font-size: 16px;">
    {{text}}
  </div>

allow_all_users: true
instances_per_annotator: 100
annotation_per_instance: 2
allow_skip: true
skip_reason_required: false