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:
# - Person, Organization, Location, Event, Date, Number, Other
#
# 17 Relation Types:
# - physical: Physical proximity or containment
# - personal-social: Personal or social relationships
# - part-whole: Component or membership
# - org-affiliation: Organizational affiliation
# - gen-affiliation: General affiliation
# - usage: One entity uses another
# - topic: Entity is about a topic
# - compare: Comparison between entities
# - origin: Entity originates from another
# - named: Entity is named after another
# - role: Entity has a role
# - temporal: Temporal relationship
# - win-defeat: Competitive outcome
# - located-in: Spatial containment
# - cause-effect: Causal relationship
# - member: Membership in a group
# - no-relation: No meaningful relation
#
# 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:
      - "physical"
      - "personal-social"
      - "part-whole"
      - "org-affiliation"
      - "gen-affiliation"
      - "usage"
      - "topic"
      - "compare"
      - "origin"
      - "named"
      - "role"
      - "temporal"
      - "win-defeat"
      - "located-in"
      - "cause-effect"
      - "member"
      - "no-relation"
    tooltips:
      "physical": "Physical proximity, containment, or spatial relationship"
      "personal-social": "Personal or social relationship between people"
      "part-whole": "Entity A is a part or component of entity B"
      "org-affiliation": "Person or entity is affiliated with an organization"
      "gen-affiliation": "General affiliation not covered by org-affiliation"
      "usage": "Entity A uses or employs entity B"
      "topic": "Entity A is about or concerns entity B"
      "compare": "Entity A is compared with entity B"
      "origin": "Entity A originates from or is derived from entity B"
      "named": "Entity A is named after entity B"
      "role": "Entity A has a role or function related to entity B"
      "temporal": "Temporal relationship between entities"
      "win-defeat": "Competitive outcome between entities"
      "located-in": "Entity A is located within entity B"
      "cause-effect": "Entity A causes or leads to entity B"
      "member": "Entity A is a member of entity B"
      "no-relation": "No meaningful relation between the entities"

  # 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