Entity Linking in Tweets

# Entity Linking in Tweets
# Based on Agarwal et al., SemEval 2022
# Paper: https://aclanthology.org/2022.semeval-1.196/
# Dataset: https://github.com/Agarwal-SemEval2022-Task12
#
# This task asks annotators to identify entity mentions in tweets and
# provide their corresponding knowledge base URIs (e.g., Wikipedia or
# Wikidata URLs). Entity mentions include persons, organizations,
# locations, events, and other named entities.
#
# Annotation Steps:
# 1. Highlight all entity mentions in the tweet text
# 2. For each entity, provide the corresponding knowledge base URI

annotation_task_name: "Entity Linking in Tweets"
task_dir: "."

data_files:
  - sample-data.json

item_properties:
  id_key: "id"
  text_key: "text"

output_annotation_dir: "annotation_output/"
output_annotation_format: "json"

port: 8000
server_name: localhost

annotation_schemes:
  - annotation_type: span
    name: entity_mentions
    description: "Highlight all named entity mentions in the tweet"
    labels:
      - "Entity Mention"

  - annotation_type: text
    name: entity_uri
    description: "Provide the knowledge base URI (e.g., Wikipedia URL) for each identified entity"

annotation_instructions: |
  You will see a tweet that may contain named entities (people, organizations, places, events, etc.).
  1. Highlight all named entity mentions in the text using the span annotation tool.
  2. For each entity, provide its corresponding knowledge base URI (Wikipedia or Wikidata URL).
  3. If multiple entities are present, list all URIs separated by semicolons.
  Note: Focus on proper nouns and named entities, not common nouns.

html_layout: |
  <div style="padding: 15px; max-width: 800px; margin: auto;">
    <div style="background: #f0f9ff; border: 1px solid #bae6fd; border-radius: 8px; padding: 16px; margin-bottom: 16px;">
      <strong style="color: #0369a1;">Tweet:</strong>
      <p style="font-size: 16px; line-height: 1.7; margin: 8px 0 0 0;">{{text}}</p>
    </div>
  </div>

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