Hi there! I’m Javad Pourmostafa /’dʒævɒd puːr’moʊs’tae’fɑː/! I go by joeybright or joyebright, wherever I can get the username. I’ve published under the name ‘Javad Pourmostafa Roshan Sharami.’ Roshan Sharami is a suffix on my last name.
I’m a Ph.D. candidate as well as a lecturer at the Department of Cognitive Science and Artificial Intelligence (CSAI) of Tilburg University, where I’m affiliated with the machine translation group (ISMT). My PhD thesis is titled “An NMT Framework based on Language Understanding.” It is divided into two main parts: (i) will investigate neural machine translation for low-resource language, e.g., Persian, through cross-lingual knowledge transfer, and (ii) aims to delve into multilingual and multi-domain adaptation. My PhD supervisors are Dr. Dimitar Shterionov and Dr. Pieter Spronck.
Prior to joining Tilburg University, I was a postgraduate member of the Guilan NLP Group and a part-time lecturer at the Computer Engineering Department of the University of Guilan. I earned my BSc and MSc degrees in Software Engineering in 2016 and 2019, respectively. During my master’s thesis, I designed sentiment analysis models using deep learning architectures for low-resource languages, with a focus on Persian. I was fortunate to work under the supervision of Dr. Seyed Abolghasem Mirroshandel.
My research mainly centralizes on natural language processing and deep learning. I’m also interested in AI more broadly.
Some topics of interest to me are:
- Machine translation
- Multilingual and multi-domain domain adaptation for NMT
- Quality Estimation
- Data Selection
- Sentiment analysis