Publications
I have published under the name Javad Pourmostafa Roshan Sharami, where Roshan Sharami is a suffix added to my last name.
Analysis of Vocabulary and Subword Tokenization Settings for Optimal Fine-tuning of MT: A Case Study of In-domain Translation
Venue: RANLP 2025: International Conference on Recent Advances in Natural Language Processing
Date: September 10, 2025, Varna, Bulgaria
Proceedings: To appear (not yet published)
Slides: PDF
Integrating SAINT with Tree-Based Models: A Case Study in Employee Attrition Prediction
Venue: IntelliSys 2025: Intelligent Systems and Applications, pp. 397–417
Date: First Online: September 3, 2025
Series: Lecture Notes in Networks and Systems
Guiding In-Context Learning of LLMs through Quality Estimation for Machine Translation
Venue: AMTA 2024: 16th Conference of the Association for Machine Translation in the Americas
Date: October 2024
Proceedings: AMTA 2024 (Volume 1: Research Track)
Evaluating the Effectiveness of Pre-trained Language Models in Predicting the Helpfulness of Online Product Reviews
Venue: IntelliSys 2023: Intelligent Systems and Applications, pp. 15–35
Date: First Online: February 14, 2024
Series: Lecture Notes in Networks and Systems (LNNS, volume 825)
A Python Tool for Selecting Domain-Specific Data in Machine Translation
Venue: Proceedings of the 1st Workshop on Open Community-Driven Machine Translation (CrowdMT 2023), co-located with EAMT 2023, Tampere, Finland
Date: June 15, 2023
Pages: 29–30
PDF: ACL Anthology
Code / Tool: GitHub: domain-adapt-mt
Tailoring Domain Adaptation for Machine Translation Quality Estimation
Venue: EAMT 2023: 24th Annual Conference of the European Association for Machine Translation (Tampere, Finland)
Date: June 2023
Pages: 9–20
Preprint / PDF: arXiv:2304.08891, ACL Anthology PDF
A Systematic Analysis of Vocabulary and BPE Settings for Optimal Fine-tuning of NMT: A Case Study of In-domain Translation
Status: Preprint
arXiv: 2303.00722
Evaluating the Effectiveness of Pre-trained Language Models in Predicting the Helpfulness of Online Product Reviews
Venue: The Intelligent Systems Conference (IntelliSys 2023)
Preprint: arXiv (ahead of publication)
Quality Estimation for the Translation Industry – Data Challenges
Venue: The 32nd Meeting of Computational Linguistics in The Netherlands (CLIN 32)
Date: June 17, 2022, Tilburg, the Netherlands
Programme: Acceptance ref.
Publication: ResearchGate
A Quality Estimation and Quality Evaluation Tool for the Translation Industry
Venue: The 23rd Annual Conference of the European Association for Machine Translation (EAMT 2022)
Publication: ACL Anthology
Selecting Parallel In-domain Sentences for Neural Machine Translation Using Monolingual Texts
Venue: Accepted to the Computational Linguistics in the Netherlands (CLIN) Journal
Timeline: Submitted Oct 13, Accepted Dec 6, 2021 (two strong accepts), Published Feb 2022
arXiv: 2112.06096
Resources: ResearchGate, CLIN, Codes, Slides
A Novel Pipeline for Domain Detection and Selecting In-domain Sentences in Machine Translation Systems
Venue: 31st Meeting of Computational Linguistics in The Netherlands (CLIN 31)
Date: July 9, 2021, Ghent, Belgium
Organized by: LT3 team
Programme: Acceptance ref.
DOI: 10.6084/m9.figshare.14829030
DeepSentiPers: Novel DL Models Trained Over Proposed Augmented Persian Sentiment Corpus
Date: April 2020
Preprint: arXiv:2004.05328
Codes: GitHub
Talk: ResearchGate
Presenting A Sentiment Analysis System Using Deep Learning Models On Persian Texts (In Persian)
Venue: 5th National Conference on Computational Linguistics of Iran
Date: November 2019, Institute for Humanities and Cultural Studies, Tehran, Iran
Organized by: Linguistics Society of Iran (LSI)
Publication: Also published as a chapter (ISBN: 978-622-6649-34-6)
Direct PDF: Download
ResearchGate: Link
DOI: 10.5281/zenodo.3551273
Certificate: Certificate of appreciation issued by LSI