MasakhaPOS - Part-of-Speech Tagging for African Languages

# MasakhaPOS - Part-of-Speech Tagging for African Languages
# Based on Dione et al., ACL 2023
# Paper: https://aclanthology.org/2023.acl-long.609/
# Dataset: https://github.com/masakhane-io/masakhane-pos
#
# MasakhaPOS provides Universal Dependencies (UD) part-of-speech annotations
# for 20 typologically diverse African languages. Annotators tag every token
# with one of the 17 universal POS tags, following the UD guidelines.
#
# The 17 Universal POS tags:
#   ADJ  adjective        ADP  adposition       ADV  adverb
#   AUX  auxiliary        CCONJ coordinating conj DET  determiner
#   INTJ interjection     NOUN noun             NUM  numeral
#   PART particle         PRON pronoun          PROPN proper noun
#   PUNCT punctuation     SCONJ subordinating conj SYM symbol
#   VERB verb             X    other
#
# Annotation Guidelines:
# 1. Read the sentence in the source language (an English gloss is provided
#    for reference in this showcase only).
# 2. Highlight EACH token in turn and assign exactly one universal POS tag.
# 3. Tag words by their function in THIS sentence, not their dictionary
#    default (e.g. the same form may be a NOUN or a VERB in context).
# 4. Multiword tokens follow the UD tokenization for the language.

annotation_task_name: "MasakhaPOS - African POS Tagging"
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: pos_tags
    description: "Highlight each token and assign its Universal POS tag"
    labels:
      - "ADJ"
      - "ADP"
      - "ADV"
      - "AUX"
      - "CCONJ"
      - "DET"
      - "INTJ"
      - "NOUN"
      - "NUM"
      - "PART"
      - "PRON"
      - "PROPN"
      - "PUNCT"
      - "SCONJ"
      - "SYM"
      - "VERB"
      - "X"
    label_colors:
      "ADJ": "#3b82f6"
      "ADP": "#64748b"
      "ADV": "#0ea5e9"
      "AUX": "#a855f7"
      "CCONJ": "#f97316"
      "DET": "#14b8a6"
      "INTJ": "#eab308"
      "NOUN": "#22c55e"
      "NUM": "#ef4444"
      "PART": "#94a3b8"
      "PRON": "#ec4899"
      "PROPN": "#16a34a"
      "PUNCT": "#9ca3af"
      "SCONJ": "#fb923c"
      "SYM": "#6b7280"
      "VERB": "#dc2626"
      "X": "#78716c"

annotation_instructions: |
  You will see a sentence written in an African language, with its language
  identifier and (for this showcase only) an English gloss.

  Highlight each token in the sentence and label it with one of the 17
  Universal Dependencies part-of-speech tags. Tag each word by the role it
  plays in this particular sentence, not by its most common usage. Content
  words are NOUN, PROPN, VERB, ADJ, ADV, NUM, INTJ; function words are ADP,
  AUX, CCONJ, SCONJ, DET, PRON, PART; and there are PUNCT, SYM, and X for
  punctuation, symbols, and anything that fits none of the above.

html_layout: |
  <div style="padding: 15px; max-width: 800px; margin: auto;">
    <div style="background: #ecfdf5; border: 1px solid #a7f3d0; border-radius: 8px; padding: 12px; margin-bottom: 12px;">
      <strong style="color: #065f46;">Language:</strong>
      <span style="font-size: 15px; margin-left: 8px;">{{language}}</span>
    </div>
    <div style="background: #f0f9ff; border: 1px solid #bae6fd; border-radius: 8px; padding: 16px; margin-bottom: 8px;">
      <strong style="color: #0369a1;">Sentence:</strong>
      <p style="font-size: 18px; line-height: 1.9; margin: 8px 0 0 0;">{{text}}</p>
    </div>
    <div style="color: #6b7280; font-size: 13px; font-style: italic; margin-bottom: 16px;">
      English gloss (reference only): {{gloss}}
    </div>
  </div>

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