1 citations · 1 across the 4 of their papers we have counts for
4 papers
IHUBERT: Vector-Based Semantic Deduplication and Domain-Balanced Pretraining for Persian Resources
Arash Ghafouri, Mahdi Firouzmandi, Hossein Saberi +1
Persian pretrained language models (PLMs) are still limited by the scarcity of large-scale, high-quality pretraining corpora and by insufficient evaluation beyond standard classifi…
A Method for Multi-Hop Question Answering on Persian Knowledge Graph
Arash Ghafouri, Mahdi Firouzmandi, Hasan Naderi
Question answering systems are the latest evolution in information retrieval technology, designed to accept complex queries in natural language and provide accurate answers using b…
PersianLLaMA: Towards Building First Persian Large Language Model
Mohammad Amin Abbasi, Arash Ghafouri, Mahdi Firouzmandi +2
Despite the widespread use of the Persian language by millions globally, limited efforts have been made in natural language processing for this language. The use of large language…
IslamicPCQA: A Dataset for Persian Multi-hop Complex Question Answering in Islamic Text Resources
Arash Ghafouri, Hasan Naderi, Mohammad Aghajani asl +1
Nowadays, one of the main challenges for Question Answering Systems is to answer complex questions using various sources of information. Multi-hop questions are a type of complex q…