Showing cs.CLShow all
3 papers · 1 filter
cs.CL2026
CANDLE: CTC-based Arabic Noisy-character Deduplication using a Lightweight Encoder
Faris Alasmary, Taif Nono, Orjuwan Zaafarani +5
Handling repeated characters in text can be tricky, since they can represent either the correct spelling of a word or informal character elongation often seen in social media posts…
cs.CL2025
Abjad AI at NADI 2025: CATT-Whisper: Multimodal Diacritic Restoration Using Text and Speech Representations
Ahmad Ghannam, Naif Alharthi, Faris Alasmary +3
In this work, we tackle the Diacritic Restoration (DR) task for Arabic dialectal sentences using a multimodal approach that combines both textual and speech information. We propose…
cs.CL2024
ArabianGPT: Native Arabic GPT-based Large Language Model
Anis Koubaa, Adel Ammar, Lahouari Ghouti +2
The predominance of English and Latin-based large language models (LLMs) has led to a notable deficit in native Arabic LLMs. This discrepancy is accentuated by the prevalent inclus…