Javad Pourmostafa Roshan Sharami

Bio

I am a PhD candidate/lecturer at the Department of Cognitive Science and Artificial Intelligence of Tilburg University. My PhD thesis 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.

Before 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.  During the master thesis, I worked on designing sentiment analysis models using deep learning architectures for low-resource languages.

My research mainly centralizes on natural language processing and deep learning. 

Some topics of interest to me are:

• Machine translation
• Multilingual and multi-domain domain adaptation for NMT
• Quality Estimation
• Data Selection
• Sentiment Analysis

Courses

• Programming with C/C++

Top publications

1. Tailoring Domain Adaptation for Machine Translation Quality Estimation

   Sharami, J. P. R., Shterionov, D., Blain, F., Vanmassenhove, E., Sisto, M. D., Emmery, C., & Spronck, P. (Accepted/In press). Tailoring Domain Adaptation for Machine Translation Quality Estimation. In Proceedings of the 24th Annual Conference of the European Association for Machine Translation (pp. 1-13)

2. A Quality Estimation and Quality Evaluation Tool for the Translation …

   Murgolo, E., Sharami, J. P. R., & Shterionov, D. (2022). A Quality Estimation and Quality Evaluation Tool for the Translation Industry. In Proceedings of the 23rd Annual Conference of the European Association for Machine Translation (pp. 305-306). European Association for Machine Translation. https://aclanthology.org/2022.eamt-1.43

3. Selecting Parallel In-domain Sentences for Neural Machine Translation…

   Pourmostafa Roshan Sharami, J., Shterionov, D., & Spronck, P. (2021). Selecting Parallel In-domain Sentences for Neural Machine Translation Using Monolingual Texts. Computational Linguistics in the Netherlands Journal, 11, 213-230.

4. A Systematic Analysis of Vocabulary and BPE Settings for Optimal Fine…

   Sharami, J. P. R., Shterionov, D., & Spronck, P. (2023). A Systematic Analysis of Vocabulary and BPE Settings for Optimal Fine-tuning of NMT: A Case Study of In-domain Translation. Manuscript submitted for publication.

5. DeepSentiPers - Novel Deep Learning Models Trained Over Proposed Augm…

   PourMostafa Roshan Sharami, J., Sarabestani, P. A., & Mirroshandel, S. A. (2020, Apr 1). DeepSentiPers - Novel Deep Learning Models Trained Over Proposed Augmented Persian Sentiment Corpus. https://arxiv.org/abs/2004.05328