NumEval - Numeral-Aware Language Understanding
Numeral-aware language understanding task requiring annotators to predict numerical values from text, classify numeral types, and provide explanations. Based on SemEval-2024 Task 7 (NumEval).
Configuration Fileconfig.yaml
# NumEval - Numeral-Aware Language Understanding
# Based on Chen et al., SemEval 2024
# Paper: https://aclanthology.org/volumes/2024.semeval-1/
# Dataset: https://github.com/SemEval/semeval-2024-task7
#
# This task asks annotators to predict numerical values from text context,
# classify the type of numeral, and provide an explanation of how they
# derived the answer.
annotation_task_name: "NumEval - Numeral-Aware Language Understanding"
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: number
name: predicted_value
description: "Predicted numerical value"
- annotation_type: radio
name: numeral_type
description: "What type of numeral is the expected answer?"
labels:
- "Exact Number"
- "Approximate"
- "Range"
- "Ordinal"
- "Other"
keyboard_shortcuts:
"Exact Number": "1"
"Approximate": "2"
"Range": "3"
"Ordinal": "4"
"Other": "5"
tooltips:
"Exact Number": "A precise numerical value (e.g., 42, 3.14)"
"Approximate": "An estimated or rounded value (e.g., about 100, roughly 50%)"
"Range": "A range of values (e.g., between 10 and 20)"
"Ordinal": "A position or rank (e.g., first, 3rd place)"
"Other": "Other numerical expressions not covered above"
- annotation_type: text
name: explanation
description: "Explain how you derived the numerical answer from the text."
annotation_instructions: |
You will be shown a text that contains or implies a numerical value. Your task is to:
1. Read the text carefully and identify the relevant numerical information.
2. Enter the predicted numerical value.
3. Classify the type of numeral (exact, approximate, range, ordinal, or other).
4. Explain your reasoning for arriving at the predicted value.
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;">Text:</strong>
<p style="font-size: 16px; line-height: 1.7; margin: 8px 0 0 0;">{{text}}</p>
</div>
<div style="background: #fefce8; border: 1px solid #fde68a; border-radius: 8px; padding: 12px;">
<strong style="color: #a16207;">Expected Answer:</strong> <span>{{expected_answer}}</span>
</div>
</div>
allow_all_users: true
instances_per_annotator: 50
annotation_per_instance: 2
allow_skip: true
skip_reason_required: false
Sample Datasample-data.json
[
{
"id": "numeval_001",
"text": "The company reported quarterly revenue of $2.3 billion, representing a 15% increase over the same period last year when revenue was [MASK].",
"expected_answer": "2.0 billion"
},
{
"id": "numeval_002",
"text": "If a train travels at 120 km/h for 2.5 hours, the total distance covered is [MASK] kilometers.",
"expected_answer": "300"
}
]
// ... and 8 more itemsGet This Design
Clone or download from the repository
Quick start:
git clone https://github.com/davidjurgens/potato-showcase.git cd potato-showcase/semeval/2024/task07-numeval potato start config.yaml
Details
Annotation Types
Domain
Use Cases
Tags
Found an issue or want to improve this design?
Open an IssueRelated Designs
Argument Reasoning in Civil Procedure
Legal argument reasoning task requiring annotators to answer multiple-choice questions about civil procedure by selecting the best answer and providing legal reasoning. Based on SemEval-2024 Task 5.
BIG-Bench Task Evaluation
Evaluate language model responses on diverse reasoning tasks from the BIG-Bench benchmark. Annotators assess correctness, provide reasoning explanations, and rate confidence for model outputs across multiple task categories.
BRAINTEASER - Commonsense-Defying QA
Lateral thinking and commonsense-defying question answering task requiring annotators to select answers to brain teasers that defy default commonsense assumptions and provide explanations. Based on SemEval-2024 Task 9 (BRAINTEASER).