Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

fix: Add namaa MrTydi reranking dataset #1573

Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions mteb/tasks/Reranking/__init__.py
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
from __future__ import annotations

from .ara.NamaaMrTydiReranking import *
from .eng.AskUbuntuDupQuestions import *
from .eng.MindSmallReranking import *
from .eng.SciDocsReranking import *
Expand Down
39 changes: 39 additions & 0 deletions mteb/tasks/Reranking/ara/NamaaMrTydiReranking.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,39 @@
from __future__ import annotations

from mteb.abstasks.TaskMetadata import TaskMetadata

from ....abstasks.AbsTaskReranking import AbsTaskReranking


class NamaaMrTydiReranking(AbsTaskReranking):
metadata = TaskMetadata(
name="NamaaMrTydiReranking",
description="Mr. TyDi is a multi-lingual benchmark dataset built on TyDi, covering eleven typologically diverse languages. It is designed for monolingual retrieval, specifically to evaluate ranking with learned dense representations. This dataset adapts the arabic test split for Reranking evaluation purposes by the addition of multiple (Hard) Negatives to each query and positive",
reference="https://huggingface.co/NAMAA-Space",
dataset={
"path": "NAMAA-Space/mteb-eval-mrtydi",
"revision": "502637220a7ad0ecc5c39ff5518d7508d2624af8",
},
type="Reranking",
category="s2s",
modalities=["text"],
eval_splits=["test"],
eval_langs=["ara-Arab"],
main_score="map",
date=("2023-11-01", "2024-05-15"),
domains=["Encyclopaedic", "Written"],
task_subtypes=[],
license="cc-by-sa-3.0",
annotations_creators="human-annotated",
dialect=[],
sample_creation="found",
bibtex_citation="""@article{muennighoff2022mteb,
doi = {10.48550/ARXIV.2210.07316},
url = {https://arxiv.org/abs/2210.07316},
author = {Muennighoff, Niklas and Tazi, Nouamane and Magne, Lo{\"\i}c and Reimers, Nils},
title = {MTEB: Massive Text Embedding Benchmark},
publisher = {arXiv},
journal={arXiv preprint arXiv:2210.07316},
year = {2022}
}""",
)
Empty file.
Loading