Kashmiri text classification resources
Labelled Kashmiri text and models for classifying it: news topics, sentiment, and telling Kashmiri apart from other languages (language identification).
- 14
- Resources2023–2026
- 6
- Datasets
- 5
- Models
- 2
- Papers
Filter this task in the full hub · Guide: Kashmiri language data
Datasets 6
OpenLID-v3
Training data for high-coverage language identification: 194 language varieties plus a not-a-language class, with labels compatible with FLORES+. Includes Kashmiri.
ILID — Indian Language Identification
250,000 sentences in English and the 22 scheduled Indian languages (10,000 Kashmiri) for training and evaluating native-script language identification.
Kashmiri News Snippet Classification Dataset (15K)
15,036 manually labelled Kashmiri news snippets across ten domains: Medical, Politics, Sports, Tourism, Education, Art & Craft, Environment, Entertainment, Technology and Culture. The first labelled Kashmiri text classification dataset.
MVL-SIB
Vision-language extension of SIB-200: image–sentence pairs across 205 languages and 7 topics for testing cross-modal topic matching.
Kashmiri Poet Dataset — Shruks
1,552 Kashmiri shruks (8,283 lines, about 36K words), offered for classification, generation and translation experiments. Access is granted on request.
SIB-200 — Topic Classification (Kashmiri)
Topic-classification benchmark for 200+ languages built on FLORES-200 sentences, with Kashmiri in both Perso-Arabic and Devanagari script (1,004 sentences each: 701 train, 99 dev, 204 test).
Models 5
SampurNER Kashmiri (IndicBERTv2)
A named-entity recognition model for Kashmiri built on IndicBERTv2.
Kashmiri BERT (kashmiri-llm-bert-base)
BERT-base model trained specifically for the Kashmiri language. Useful for downstream tasks like text classification, NER, and feature extraction.
IndicLID — Language Identification for Indian Languages
Language identifier for Indian languages that recognises Kashmiri in Perso-Arabic (kas_Arab), Devanagari (kas_Deva) and Latin (kas_Latn) script.
BLOOM-560M
Open multilingual LLM pretrained on ROOTS corpus (incl. Persian/Urdu). Used for zero-shot Kashmiri text classification. Effective for cross-lingual transfer to Kashmiri.
IndicBERTv2 (ai4bharat)
Multilingual BERT model pretrained on Indian languages including Kashmiri. Used as embedding backbone in news classification benchmarks (F1=0.98 with GRU).
Papers 2
Dataset Creation & Benchmarking for Kashmiri News Snippet Classification
First manually labeled corpus of 15,036 Kashmiri news snippets across 10 domains. Benchmarks ParsBERT (F1=0.98), IndicBERTv2+GRU, BLOOM-560m, and Flan-T5 in zero-shot settings.
EnsembleSenti-Kash: Stacked Ensemble for Kashmiri Sentiment Classification
A stacked ensemble learning system for Kashmiri sentiment analysis with manually labeled data. Compares SVM, Random Forest, XGBoost, mBERT, and LSTM architectures.