CrossRE: Cross-Domain Relation Extraction

# CrossRE: Cross-Domain Relation Extraction
# Based on Bassignana & Plank, Findings EMNLP 2022
# Paper: https://aclanthology.org/2022.findings-emnlp.263/
# Dataset: https://github.com/mainlp/CrossRE
#
# CrossRE provides relation extraction annotations across 6 diverse domains:
# news, politics, natural science, music, literature, and AI.
# This enables studying how relation extraction models transfer across domains.
#
# Entity Types (simplified):
# CrossRE reuses CrossNER's fine-grained, per-domain named-entity types.
# This template uses a generic set (Person, Organization, Location, Event,
# Date, Number, Other) as a simplification.
#
# 17 Relation Types (CrossRE):
# - artifact: something produced/created by an entity (written_by, made_by)
# - cause-effect: one entity causes or leads to another
# - compare: comparison between entities
# - general-affiliation: general affiliation
# - named: entity is named after another
# - opposite: opposition or antonymy between entities
# - origin: entity originates from another
# - part-of: one entity is part of another
# - physical: physical or spatial relationship
# - related-to: general relatedness not covered above
# - role: business-related role (member_of, founder, citizen_of)
# - social: non-business personal/social relationship
# - temporal: temporal relationship
# - topic: entity is about a topic
# - type-of: one entity is a type of another
# - usage: one entity makes use of another
# - win-defeat: outcome of a competition, award, or war
#
# Note: CrossRE has no "no-relation" label; unrelated pairs are left
# unlinked, and a pair may carry more than one relation label.
#
# Annotation Guidelines:
# 1. Read the sentence and note the domain
# 2. Identify all named entities and classify them
# 3. For each entity pair, determine the relation type
# 4. Optionally add notes about ambiguous cases

annotation_task_name: "CrossRE: Cross-Domain 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 entities
  - annotation_type: span
    name: entities
    description: "Highlight all entities in the text"
    labels:
      - "Person"
      - "Organization"
      - "Location"
      - "Event"
      - "Date"
      - "Number"
      - "Other"
    label_colors:
      "Person": "#3b82f6"
      "Organization": "#22c55e"
      "Location": "#ef4444"
      "Event": "#f59e0b"
      "Date": "#8b5cf6"
      "Number": "#06b6d4"
      "Other": "#6b7280"
    keyboard_shortcuts:
      "Person": "1"
      "Organization": "2"
      "Location": "3"
      "Event": "4"
      "Date": "5"
      "Number": "6"
      "Other": "7"
    tooltips:
      "Person": "Names of people, including fictional characters"
      "Organization": "Companies, institutions, bands, teams, political parties"
      "Location": "Countries, cities, geographic regions, addresses"
      "Event": "Named events, wars, festivals, elections, discoveries"
      "Date": "Dates, years, time periods, centuries"
      "Number": "Numerical values, quantities, measurements"
      "Other": "Entities not fitting other categories (works of art, products, etc.)"
    allow_overlapping: false

  # Step 2: Link entities with relation types
  - annotation_type: span_link
    name: relations
    description: "Draw relations between entity pairs"
    labels:
      - "artifact"
      - "cause-effect"
      - "compare"
      - "general-affiliation"
      - "named"
      - "opposite"
      - "origin"
      - "part-of"
      - "physical"
      - "related-to"
      - "role"
      - "social"
      - "temporal"
      - "topic"
      - "type-of"
      - "usage"
      - "win-defeat"
    tooltips:
      "artifact": "Something produced or created by an entity (written_by, made_by)"
      "cause-effect": "One entity causes or leads to another"
      "compare": "Comparison between entities"
      "general-affiliation": "General affiliation between entities"
      "named": "Entity is named after another"
      "opposite": "Opposition or antonymy between entities"
      "origin": "Entity originates from or is derived from another"
      "part-of": "One entity is part or component of another"
      "physical": "Physical or spatial relationship (Where?)"
      "related-to": "General relatedness not covered by other labels"
      "role": "Business-related role (member_of, founder, citizen_of)"
      "social": "Non-business personal or social relationship"
      "temporal": "Temporal relationship between entities"
      "topic": "Entity is about a topic"
      "type-of": "One entity is a type of another"
      "usage": "One entity makes use of another (agent/instrument)"
      "win-defeat": "Outcome of a competition, award, or war"

  # Step 3: Optional annotator notes
  - annotation_type: text
    name: notes
    description: "Optional notes about ambiguous cases or difficult decisions"

html_layout: |
  <div style="margin-bottom: 10px; padding: 8px; background: #f0f4f8; border-radius: 4px;">
    <strong>Domain:</strong> {{domain}}
  </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