Skip to content
This repository was archived by the owner on Feb 4, 2025. It is now read-only.

Conversation

@SaileshP97
Copy link

This pull request introduces a comprehensive Hindi Leaderboard that supports six distinct tasks, including clustering, classification, STS, pair classification, retrieval, and reranking. A total of 21 datasets have been added, covering a wide range of benchmarks for evaluating performance in Hindi NLP.

Tasks and Datasets Included:

Clustering

IndicReviewsClusteringP2P
SIB200ClusteringS2S

Classification

HindiDiscourseClassification
SentimentAnalysisHindi
MassiveIntentClassification
MassiveScenarioClassification
MTOPIntentClassification
MultiHateClassification
SIB200Classification
TweetSentimentClassification
IndicSentimentClassification

Semantic Textual Similarity (STS)

SemRel24STS

Pair Classification

XNLI

Retrieval

BelebeleRetrieval
IndicQARetrieval
MintakaRetrieval
MIRACLRetrievalHardNegatives
MultiLongDocRetrieval
WikipediaRetrievalMultilingual

Reranking

MIRACLReranking
WikipediaRerankingMultilingual

@Samoed
Copy link
Member

Samoed commented Jan 27, 2025

Please remove all_data_tasks and boards_data from the changes, as they will be updated automatically after the PR is merged. Including them now will cause a lot of merge conflicts.

@SaileshP97 SaileshP97 closed this Jan 27, 2025
@SaileshP97 SaileshP97 deleted the Hindi_leaderboard branch January 27, 2025 13:04
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants