PreTENS - Presuppositional Acceptability
Judge the acceptability of sentences whose two nominal arguments are presupposed to stand (or not) in an ordered taxonomic relation. Includes a binary acceptable/unacceptable judgment and a 1-7 acceptability rating. Based on SemEval-2022 Task 3 (Zamparelli et al.).
Get This Design
Clone or download from the repository
Quick start:
git clone https://github.com/davidjurgens/potato-showcase.git
cd potato-showcase/semeval/2022/task03-pretens
potato start config.yamlConfiguration File
This Potato config reproduces the annotation task. Save it as config.yaml and run potato start config.yaml to try it.
# PreTENS - Presuppositional Acceptability
# Based on Zamparelli et al., SemEval 2022
# Paper: https://aclanthology.org/2022.semeval-1.29/
# Dataset: https://github.com/shammur/SemEval2022Task3
#
# This task asks annotators to judge whether a sentence is acceptable given the
# taxonomic relation presupposed between its two nominal arguments. Sentences use
# constructions (comparatives, exemplifications, generalizations) that presuppose
# one argument is a supercategory or subcategory of the other, e.g.
# "I like trees, and in particular birches" (acceptable) vs.
# "I like birches, and in particular trees" (unacceptable).
#
# Subtask 1 (binary): Acceptable vs. Unacceptable.
# Subtask 2 (regression): a 1-7 acceptability rating.
annotation_task_name: "PreTENS - Presuppositional Acceptability"
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: radio
name: acceptability
description: "Is this sentence acceptable?"
labels:
- "Acceptable"
- "Unacceptable"
keyboard_shortcuts:
"Acceptable": "1"
"Unacceptable": "2"
tooltips:
"Acceptable": "The taxonomic relation between the two arguments fits the construction (e.g. a subcategory exemplifies its supercategory)"
"Unacceptable": "The taxonomic relation is reversed or does not hold, making the sentence odd (e.g. a supercategory presented as an example of its subcategory)"
- annotation_type: likert
name: acceptability_rating
description: "How acceptable is this sentence?"
size: 7
min_label: "Not at all acceptable"
max_label: "Completely acceptable"
annotation_instructions: |
Each sentence relates two nominal arguments (e.g. "trees" and "birches") through a
construction such as a comparison, an exemplification, or a generalization. The
construction presupposes a taxonomic relation between the arguments -- typically that
one is a supercategory (superset) of the other.
- Acceptable: The presupposed taxonomic relation holds. For example, an exemplification
should introduce a subcategory of the more general term ("I like trees, and in
particular birches").
- Unacceptable: The relation is reversed or does not hold, so the sentence is odd
("I like birches, and in particular trees").
Judge acceptability of the meaning, not grammar. A grammatically correct sentence can
still be unacceptable. Then give an overall acceptability rating from 1 (not at all
acceptable) to 7 (completely acceptable).
html_layout: |
<div style="padding: 15px; max-width: 800px; margin: auto;">
<div style="background: #faf5ff; border: 1px solid #e9d5ff; border-radius: 8px; padding: 12px; margin-bottom: 12px;">
<strong style="color: #7e22ce;">Construction:</strong>
<span style="font-size: 15px; margin-left: 8px;">{{construction_type}}</span>
</div>
<div style="background: #f0f9ff; border: 1px solid #bae6fd; border-radius: 8px; padding: 16px; margin-bottom: 16px;">
<strong style="color: #0369a1;">Sentence:</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: 3
allow_skip: true
skip_reason_required: false
Sample Data
[
{
"id": "pretens_001",
"text": "I like trees, and in particular birches.",
"construction_type": "Exemplification"
},
{
"id": "pretens_002",
"text": "I like birches, and in particular trees.",
"construction_type": "Exemplification"
}
]
// ... 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/2022/task03-pretens
potato start config.yamlDataset & paper
Zamparelli et al., SemEval 2022
Citation (BibTeX)
@inproceedings{zamparelli-etal-2022-semeval,
title = "{S}em{E}val-2022 Task 3: {P}re{TENS}-Evaluating Neural Networks on Presuppositional Semantic Knowledge",
author = "Zamparelli, Roberto and Chowdhury, Shammur and Brunato, Dominique and Chesi, Cristiano and Dell{'}Orletta, Felice and Hasan, Md. Arid and Venturi, Giulia",
booktitle = "Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.semeval-1.29/",
doi = "10.18653/v1/2022.semeval-1.29",
pages = "228--238"
}Details
Annotation Types
Domain
Use Cases
Tags
Found an issue or want to improve this design?
Open an Issue(opens in a new tab)Related Designs
Assessing Humor in Edited News Headlines
Rate the funniness of edited news headlines on a 0-3 scale and judge which of two edited versions is funnier, based on SemEval-2020 Task 7 (Hossain et al.). Headlines are minimally edited by replacing a single word to create humorous effect.
Fine-Grained Sentiment Analysis on Financial Microblogs and News
Graded sentiment analysis of financial text with topic classification, rating market sentiment from very bearish to very bullish on a 7-point scale. Based on SemEval-2017 Task 5.
MTRAGEval: Evaluating Multi-Turn RAG Conversations
SemEval-2026 Task 8 (MTRAGEval): evaluating retrieval-augmented generation (RAG) in multi-turn conversations, built on the MTRAG benchmark. Given a conversation, the retrieved reference passages, and a system-generated response, annotators judge how faithful the response is to the passages, how well it answers the user's latest question, and whether it correctly handles unanswerable, underspecified, non-standalone, or unclear questions. The shared task covers retrieval (A), generation (B), and full RAG (C).