Skip to content

[mieb] fix hatefulmemes #2531

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.

Sign up for GitHub

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

Merged
isaac-chung merged 2 commits into from
Apr 12, 2025
Merged

[mieb] fix hatefulmemes #2531

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
5345d34
fix hatefulmeme
gowitheflow-1998 Apr 10, 2025
4e9d1f5
add to description and use polars instead
isaac-chung Apr 12, 2025
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
10 changes: 7 additions & 3 deletions mteb/tasks/Image/Any2AnyRetrieval/eng/HatefulMemesI2TRetrieval.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
from __future__ import annotations

import polars as pl
from datasets import concatenate_datasets, load_dataset

from mteb.abstasks.Image.AbsTaskAny2AnyRetrieval import AbsTaskAny2AnyRetrieval
Expand All @@ -16,9 +17,13 @@ def _load_data(path: str, splits: str, cache_dir: str = None, revision: str = No
cache_dir=cache_dir,
revision=revision,
)
dataset_splits = list(dataset)
dataset_splits = ["test", "validation", "train"]
shared_corpus = concatenate_datasets([dataset[split] for split in dataset_splits])

text_df = pl.DataFrame({"text": shared_corpus["text"]})
unique_indices = text_df["text"].arg_unique()
shared_corpus = shared_corpus.select(unique_indices)

shared_corpus = shared_corpus.map(
lambda x: {
"id": "corpus-" + str(x["id"]),
Expand Down Expand Up @@ -61,12 +66,11 @@ def _load_data(path: str, splits: str, cache_dir: str = None, revision: str = No
class HatefulMemesI2TRetrieval(AbsTaskAny2AnyRetrieval):
metadata = TaskMetadata(
name="HatefulMemesI2TRetrieval",
description="Retrieve captions based on memes.",
description="Retrieve captions based on memes to assess OCR abilities.",
reference="https://arxiv.org/pdf/2005.04790",
dataset={
"path": "Ahren09/MMSoc_HatefulMemes",
"revision": "c9a9a6c3ef0765622a6de0af6ebb68f323ad73ba",
# "trust_remote_code": True,
},
type="Any2AnyRetrieval",
category="i2t",
Expand Down
10 changes: 7 additions & 3 deletions mteb/tasks/Image/Any2AnyRetrieval/eng/HatefulMemesT2IRetrieval.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
from __future__ import annotations

import polars as pl
from datasets import concatenate_datasets, load_dataset

from mteb.abstasks.Image.AbsTaskAny2AnyRetrieval import AbsTaskAny2AnyRetrieval
Expand All @@ -16,9 +17,13 @@ def _load_data(path: str, splits: str, cache_dir: str = None, revision: str = No
cache_dir=cache_dir,
revision=revision,
)
dataset_splits = list(dataset)
dataset_splits = ["test", "validation", "train"]
shared_corpus = concatenate_datasets([dataset[split] for split in dataset_splits])

text_df = pl.DataFrame({"text": shared_corpus["text"]})
unique_indices = text_df["text"].arg_unique()
shared_corpus = shared_corpus.select(unique_indices)

shared_corpus = shared_corpus.map(
lambda x: {
"id": "corpus-" + str(x["id"]),
Expand Down Expand Up @@ -61,12 +66,11 @@ def _load_data(path: str, splits: str, cache_dir: str = None, revision: str = No
class HatefulMemesT2IRetrieval(AbsTaskAny2AnyRetrieval):
metadata = TaskMetadata(
name="HatefulMemesT2IRetrieval",
description="Retrieve captions based on memes.",
description="Retrieve captions based on memes to assess OCR abilities.",
reference="https://arxiv.org/pdf/2005.04790",
dataset={
"path": "Ahren09/MMSoc_HatefulMemes",
"revision": "c9a9a6c3ef0765622a6de0af6ebb68f323ad73ba",
# "trust_remote_code": True,
},
type="Any2AnyRetrieval",
category="t2i",
Expand Down