image
Soroush Faridan
NLP Researcher

Soroush Faridan

I am currently a PhD student in artificial intelligence at the Applied Data Mining research group, Queensland University of Technology, Australia. Prior to joining QUT, I received my bachelor's and master's degrees in information technology. My master's research was centred around combining word embeddings for the Persian language inference task. In another part of my master's thesis, I contributed to collecting the first Persian dataset for natural language inference task in a team effort. My research interests mainly lie in natural language processing, text mining, machine learning, and more broadly data science.


Email: soroush.faridanjahromi@hdr.qut.edu.au

CV

Curriculum Vitae

Education

Mar 2024 – Present
Queensland University of Technology
Brisbane
Australia

PhD in Artificial Intelligence

Supervisor: Prof Richi Nayak

Sep 2017 – Oct 2020
University of Qom
Qom
Iran

MSc in Information Technology

GPA: 85.3%
Thesis: "Combining contextualized and context-independent word embeddings in Persian language inference"
Supervisor: Dr Hossein Amirkhani

Sep 2012 – Feb 2017
Jahrom University
Jahrom
Iran

BSc in Information Technology

Thesis: "Key success factors in technology transfer"
Supervisor: Dr Mohammad Ebrahim Samie



Publications



Projects

  • FarsTail dataset

    FarsTail is the first relatively large-scale Persian dataset for Natural Language Inference (NLI) task with more than 10,000 samples. To ensure the quality of FarsTail, the data preparation process is almost similar to the well-known SciTail dataset, and several steps of cleaning and relabeling have been performed on this dataset. Along with the raw Persian samples, we provide the indexed format of FarsTail to be usable for non-Persian researchers as well.

  • Predicting a banking indicator from news texts

    I applied NLP techniques on crawled news texts of recent years to predict monthly changes in one of the most important indicators of Liquidity Risk Management in Banks.



Presentations



Experience

Jul 2024 – Present
Queensland University of Technology
Brisbane
Australia

Academic Tutor

  • IFN509 Data Exploration and Mining
  • CAB330 Data and Web Analytics
Sep 2019 – Jun 2022
University of Qom
Qom
Iran

Teaching Assistant

  • Graded 250+ assignments in some courses, including Data Mining (3 semesters), Research Methodology (2 semesters), and Computational Intelligence (1 semester)
  • Held several online meetings with students to debug and grade their projects
Nov 2017 – Apr 2018
Railway Transportation Company
Tehran
Iran

Software Test Intern

  • Tested the Electronic Bill of Lading software (Windows Application and Web Application) and reported the issues to the lead developer
  • Solved software problems remotely for each of the railways in other cities
Jul 2017 – Sep 2017
Shian Job Classification Technical Consulting Office
Shiraz
Iran

Excel Specialist

  • Created professional Excel spreadsheets for the documents of job classification
Sep 2016 – Jun 2017
Darolekram Charity
Jahrom
Iran

IT Specialist

  • Handled all IT work in the office, such as troubleshooting computers and devices


Professional Activities

Aug 2023 – Present
Springer

Journal Reviewer

Soft Computing

Dec 2022 – Present
Elsevier

Journal Reviewer

Expert Systems with Applications

Sep 2018 – Oct 2020
Data Mining & Machine Learning Lab of University of Qom

Member

Attended weekly meetings where the latest Natural Language Processing papers were presented and discussed by members

Research Interests

  • Natural Language Processing
  • Machine Learning
  • Text Mining
  • Data Mining
  • Deep Learning
  • Data Science
  • Artificial Intelligence
  • Business Intelligence


Skills

Programming Languages
  • Python
  • SQL
  • MATLAB
  • C++
Machine Learning Frameworks
  • PyTorch
  • Keras
  • scikit-learn
  • NLTK
  • spaCy
  • Gensim
Analytical Tools
  • RapidMiner
  • Microsoft Excel
  • Microsoft Power BI
  • Tableau
Typesetting
  • LaTeX
  • Microsoft Word
Web Programming
  • HTML
  • CSS
  • JavaScript
Version Control
  • Git


Languages

  • Persian: Native
  • English: Fluent
    • PTE Academic Score (ranges between 10–90)
    Listening
    Reading
    Speaking
    Writing
    Overall
    60
    59
    63
    63
    62


Certificates

  • Introduction to Machine Learning (by Coursera)
  • Recurrent Neural Networks for Language Modeling in Python (by DataCamp)
  • Feature Engineering for NLP in Python (by DataCamp)
  • Advanced NLP with spaCy (by DataCamp)


Honors and Awards

  • QUT Postgraduate Research Award (QUTPRA) (2024–2028)
  • MACSYS Top-Up Scholarship (2024–2028)
  • Ranked among top 3% in the Nationwide University Entrance Exam for MSc in Information Technology (2017)
CV

Contact

Get in touch

Email

Google Scholar

LinkedIn

ResearchGate

Scopus

Clarivate

GitHub

ORCID

Semantic Scholar

DBLP

arXiv

Stack Overflow

ADS

Facebook

Twitter