FLARE - Financial Named Entity Recognition

# FLARE - Financial Named Entity Recognition
# Based on the FLARE benchmark introduced in PIXIU (Xie et al., NeurIPS 2023 Datasets & Benchmarks)
# Paper: https://arxiv.org/abs/2306.05443
# Dataset: https://github.com/The-FinAI/PIXIU
#
# Annotate financial text for named entities and classify document types.
# Entity types include companies, persons, currencies, monetary amounts,
# dates, percentages, and stock ticker symbols.
#
# Entity Types:
# - Company: Corporate entity names (e.g., Apple Inc., Goldman Sachs)
# - Person: Individual names (e.g., CEO names, analysts)
# - Currency: Currency names or codes (e.g., USD, Euro, Japanese yen)
# - Amount: Monetary values (e.g., $5.2 billion, 150 million)
# - Date: Temporal expressions (e.g., Q3 2024, fiscal year 2023)
# - Percentage: Percentage values (e.g., 12%, 3.5 percent)
# - Stock Ticker: Exchange symbols (e.g., AAPL, MSFT, GOOGL)
#
# Document Types:
# - Earnings Report: Quarterly or annual financial results
# - Market Analysis: Commentary on market trends and outlook
# - Regulatory Filing: SEC filings, compliance documents
# - Merger/Acquisition: M&A announcements and deal coverage
# - Other: General financial news or other document types
#
# Guidelines:
# 1. Mark all entity spans precisely (do not include surrounding punctuation)
# 2. Label each span with the appropriate entity type
# 3. Classify the overall document type based on content

annotation_task_name: "FLARE: Financial 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"

port: 8000
server_name: localhost

annotation_schemes:
  - annotation_type: span
    name: financial_entities
    description: "Highlight and label financial entities in the text"
    labels:
      - "Company"
      - "Person"
      - "Currency"
      - "Amount"
      - "Date"
      - "Percentage"
      - "Stock Ticker"
    tooltips:
      "Company": "Corporate entity name (e.g., Apple Inc., Goldman Sachs Group)"
      "Person": "Individual name, typically executives, analysts, or public figures"
      "Currency": "Currency name or code (e.g., USD, Euro, British pound)"
      "Amount": "Monetary value with or without currency symbol (e.g., $5.2 billion)"
      "Date": "Temporal expression including quarters, years, and specific dates"
      "Percentage": "Percentage value (e.g., 12%, 3.5 percent)"
      "Stock Ticker": "Stock exchange ticker symbol (e.g., AAPL, MSFT)"

  - annotation_type: radio
    name: document_type
    description: "What type of financial document is this text from?"
    labels:
      - "Earnings Report"
      - "Market Analysis"
      - "Regulatory Filing"
      - "Merger/Acquisition"
      - "Other"
    keyboard_shortcuts:
      "Earnings Report": "1"
      "Market Analysis": "2"
      "Regulatory Filing": "3"
      "Merger/Acquisition": "4"
      "Other": "5"
    tooltips:
      "Earnings Report": "Quarterly or annual financial results and performance discussion"
      "Market Analysis": "Commentary on market trends, forecasts, and economic outlook"
      "Regulatory Filing": "SEC filings, compliance documents, legal/regulatory matters"
      "Merger/Acquisition": "M&A announcements, deal terms, acquisition coverage"
      "Other": "General financial news, press releases, or other document types"

annotation_instructions: |
  Annotate financial text for named entities and classify the document type.

  For each item:
  1. Read the financial text carefully.
  2. Use the span tool to highlight all financial entities and assign the correct label.
  3. Classify the overall document type.

  Entity annotation tips:
  - Mark entity spans precisely (e.g., "Apple Inc." not "Apple Inc. reported")
  - Include full company names but not surrounding text
  - Mark all instances of each entity, even if repeated
  - Stock tickers should include just the symbol (e.g., "AAPL")

html_layout: |
  <div style="padding: 15px; max-width: 800px; margin: auto;">
    <div style="background: #f0f9ff; border: 1px solid #bae6fd; border-radius: 8px; padding: 16px;">
      <strong style="color: #0369a1;">Financial Text:</strong>
      <p style="font-size: 16px; line-height: 1.8; 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