Javad Pourmostafa Roshan Sharami

Bio

I am currently a first-year PhD candidate at the Department of Cognitive Science and Artificial Intelligence of Tilburg University. My PhD thesis, entitled “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. 

Before joining Tilburg University, I was a postgraduate member at Guilan NLP Group and a part-time lecturer at the Computer Engineering Department of the University of Guilan. I graduated with an MS degree in Software Engineering from the same university in 2019. During the master thesis, I worked on designing sentiment analysis models using deep learning architectures for low-resources corpora (case-study: Persian).

Top publications

1. A Novel Pipeline for Domain Detection and Selecting In-domain Sentenc…

   Pourmostafa Roshan Sharami, J., Shterionov, D., & Spronck, P. (2021). A Novel Pipeline for Domain Detection and Selecting In-domain Sentences in Machine Translation Systems. Poster session presented at The 31st Meeting of Computational Linguistics in The Netherlands (CLIN 31), Ghent, Belgium.

2. 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