Sawsan Alqahtani

2 paper cards in Mova's library · 2020–2026

Sawsan Alqahtani wrote 2 of the papers Mova reads, in 2020–2026; often with Ajay Mishra, Chatrine Qwaider, Hanan Aldarmaki.

The profile is the library's match of the name; two people with one name are not always told apart.

Papers

Morphemes without Borders: Evaluating Root–Pattern Morphology in Arabic Tokenizers and LLMs (2026)
The authors ask whether the tokenizers of seven LLMs (GPT-4, GPT-4o, LLaMA 3, Qwen 3, Cohere, and the Arabic-centric Fanar and ALLaM) keep Arabic morphemes intact.
A Multitask Learning Approach for Diacritic Restoration (2020)
Diacritic restoration for Arabic (adding the short vowels to undiacritized text) is usually done by a character-level BiLSTM, which can lose word-level information.