REDFM: Filtered and Multilingual Relation Extraction

# REDFM: Filtered and Multilingual Relation Extraction
# Based on Huguet Cabot et al., ACL 2023
# Paper: https://aclanthology.org/2023.acl-long.367/
# Dataset: https://huggingface.co/datasets/DFKI-SLT/REDFM
#
# REDFM is a large-scale multilingual relation extraction dataset derived
# from Wikidata, covering 20+ languages with curated relation types.
# The dataset uses distant supervision from Wikidata, with filtering
# to reduce noise and improve annotation quality.
#
# Languages include: English, French, German, Spanish, Italian, Portuguese,
# Chinese, Japanese, Korean, Arabic, Hindi, Russian, and more.
#
# Entity Types:
# - Person, Organization, Location, Date, Event, Work, Other
#
# Relation Types (subset of common Wikidata properties):
# - country (P17): Located in country
# - instance_of (P31): Is an instance of
# - part_of (P361): Is a part of
# - occupation (P106): Has occupation
# - located_in (P131): Located in administrative entity
# - birth_place (P19): Place of birth
# - death_place (P20): Place of death
# - nationality (P27): Country of citizenship
# - employer (P108): Employed by
# - educated_at (P69): Educated at institution
# - author (P50): Author of work
# - genre (P136): Genre of work
# - capital (P36): Capital city of
# - language (P407): Language of work or name
# - inception (P571): Date of inception
#
# Annotation Guidelines:
# 1. Read the sentence and note the language
# 2. Verify that subject and object entity spans are correct
# 3. Identify and label all entities in the text
# 4. For each entity pair, select the Wikidata relation type
# 5. If no relation applies, skip the pair

annotation_task_name: "REDFM: Multilingual Relation Extraction"
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:
  # Step 1: Identify and verify entity spans
  - annotation_type: span
    name: entities
    description: "Highlight all entities in the text and verify subject/object spans"
    labels:
      - "Person"
      - "Organization"
      - "Location"
      - "Date"
      - "Event"
      - "Work"
      - "Other"
    label_colors:
      "Person": "#3b82f6"
      "Organization": "#22c55e"
      "Location": "#ef4444"
      "Date": "#8b5cf6"
      "Event": "#f59e0b"
      "Work": "#06b6d4"
      "Other": "#6b7280"
    keyboard_shortcuts:
      "Person": "1"
      "Organization": "2"
      "Location": "3"
      "Date": "4"
      "Event": "5"
      "Work": "6"
      "Other": "7"
    tooltips:
      "Person": "Names of people (any language)"
      "Organization": "Companies, institutions, governments, groups"
      "Location": "Countries, cities, geographic features, addresses"
      "Date": "Dates, years, time periods"
      "Event": "Named events, wars, elections, festivals"
      "Work": "Books, films, songs, artworks, software"
      "Other": "Entities not fitting other categories"
    allow_overlapping: false

  # Step 2: Link entities with Wikidata relation types
  - annotation_type: span_link
    name: wikidata_relations
    description: "Draw relations between entity pairs using Wikidata property types"
    labels:
      - "country (P17)"
      - "instance_of (P31)"
      - "part_of (P361)"
      - "occupation (P106)"
      - "located_in (P131)"
      - "birth_place (P19)"
      - "death_place (P20)"
      - "nationality (P27)"
      - "employer (P108)"
      - "educated_at (P69)"
      - "author (P50)"
      - "genre (P136)"
      - "capital (P36)"
      - "language (P407)"
      - "inception (P571)"
    tooltips:
      "country (P17)": "Entity is located in or belongs to this country"
      "instance_of (P31)": "Entity is an instance of a class or type"
      "part_of (P361)": "Entity is a part or component of another entity"
      "occupation (P106)": "Person has this occupation or profession"
      "located_in (P131)": "Entity is located in this administrative territory"
      "birth_place (P19)": "Person was born in this location"
      "death_place (P20)": "Person died in this location"
      "nationality (P27)": "Person holds citizenship of this country"
      "employer (P108)": "Person is employed by this organization"
      "educated_at (P69)": "Person was educated at this institution"
      "author (P50)": "Work was authored by this person"
      "genre (P136)": "Work belongs to this genre or category"
      "capital (P36)": "Location is the capital of this entity"
      "language (P407)": "Work or name is in this language"
      "inception (P571)": "Entity was created or founded at this date"

html_layout: |
  <div style="margin-bottom: 10px; padding: 8px; background: #f0f4f8; border-radius: 4px;">
    <strong>Language:</strong> {{language}} |
    <strong>Subject:</strong> {{subject_entity}} |
    <strong>Object:</strong> {{object_entity}}
  </div>
  <div style="font-size: 16px; line-height: 1.6;">
    {{text}}
  </div>

allow_all_users: true
instances_per_annotator: 50
annotation_per_instance: 2
allow_skip: true
skip_reason_required: false