# Konooz: Multi-domain Multi-dialect Corpus for Named Entity Recognition

arXiv: https://arxiv.org/abs/2506.12615 · HTML: https://mlsanity.com/paper/2506.12615/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 46 references that are in the map.
- First posted on arXiv 14 Jun 2025.

## Builds on (most cited first, 22 of 22)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [AraBERT: Transformer-based Model for Arabic Language Understanding](https://mlsanity.com/paper/2003.00104/) (2020)
- [A Panoramic Survey of Natural Language Processing in the Arab World](https://mlsanity.com/paper/2011.12631/) (2020)
- [Wojood: Nested Arabic Named Entity Corpus and Recognition using BERT](https://mlsanity.com/paper/2205.09651/) (2022)
- [Domain Divergences: a Survey and Empirical Analysis](https://mlsanity.com/paper/2010.12198/) (2020)
- [ALDi: Quantifying the Arabic Level of Dialectness of Text](https://mlsanity.com/paper/2310.13747/) (2023)
- [Casablanca: Data and Models for Multidialectal Arabic Speech Recognition](https://mlsanity.com/paper/2410.04527/) (2024)
- [The Arabic Ontology -- An Arabic Wordnet with Ontologically Clean Content](https://mlsanity.com/paper/2205.09664/) (2022)
- [ArabGlossBERT: Fine-Tuning BERT on Context-Gloss Pairs for WSD](https://mlsanity.com/paper/2205.09685/) (2022)
- [Using Similarity Measures to Select Pretraining Data for NER](https://mlsanity.com/paper/1904.00585/) (2019)
- [Are Large Language Models the New Interface for Data Pipelines?](https://mlsanity.com/paper/2406.06596/) (2024)
- [What do we Really Know about State of the Art NER?](https://mlsanity.com/paper/2205.00034/) (2022)
- [SALMA: Arabic Sense-Annotated Corpus and WSD Benchmarks](https://mlsanity.com/paper/2310.19029/) (2023)
- [Sebastian, Basti, Wastl?! Recognizing Named Entities in Bavarian Dialectal Data](https://mlsanity.com/paper/2403.12749/) (2024)
- [Arabic Fine-Grained Entity Recognition](https://mlsanity.com/paper/2310.17333/) (2023)
- [WojoodNER 2023: The First Arabic Named Entity Recognition Shared Task](https://mlsanity.com/paper/2310.16153/) (2023)
- [WojoodNER 2024: The Second Arabic Named Entity Recognition Shared Task](https://mlsanity.com/paper/2407.09936/) (2024)
- [Qabas: An Open-Source Arabic Lexicographic Database](https://mlsanity.com/paper/2406.06598/) (2024)
- [Event-Arguments Extraction Corpus and Modeling using BERT for Arabic](https://mlsanity.com/paper/2407.21153/) (2024)
- [ArabicNLU 2024: The First Arabic Natural Language Understanding Shared Task](https://mlsanity.com/paper/2407.20663/) (2024)
- [Predicting the Success of Domain Adaptation in Text Similarity](https://mlsanity.com/paper/2106.04641/) (2021)

## Built on by (most cited first, 3 of 3)

- [NADI 2025: The First Multidialectal Arabic Speech Processing Shared Task](https://mlsanity.com/paper/2509.02038/) (2025)
- [Cross-Dialect NER for Bangla Regional Dialects Using Leave-One-Dialect-Out Cross-Validation and Explainable AI](https://mlsanity.com/paper/2609.22536/) (2026)
- [U4RASD at KnowledgeGraphEval-2026: Ontology-Constrained Encoder and LLM Systems for Arabic Relation Extraction](https://mlsanity.com/paper/2610.12742/) (2026)

## Abstract (arXiv)

We introduce Konooz, a novel multi-dimensional corpus covering 16 Arabic dialects across 10 domains, resulting in 160 distinct corpora. The corpus comprises about 777k tokens, carefully collected and manually annotated with 21 entity types using both nested and flat annotation schemes - using the Wojood guidelines. While Konooz is useful for various NLP tasks like domain adaptation and transfer learning, this paper primarily focuses on benchmarking existing Arabic Named Entity Recognition (NER) models, especially cross-domain and cross-dialect model performance. Our benchmarking of four Arabic NER models using Konooz reveals a significant drop in performance of up to 38% when compared to the in-distribution data. Furthermore, we present an in-depth analysis of domain and dialect divergence and the impact of resource scarcity. We also measured the overlap between domains and dialects using the Maximum Mean Discrepancy (MMD) metric, and illustrated why certain NER models perform better on specific dialects and domains. Konooz is open-source and publicly available at https://sina.birzeit.edu/wojood/#download