Salman Farsi

Salman Farsi

Graduated from Chittagong University of Engineering and Technology (CUET). Interested in software development and natural language processing.

Research Interest

My broad research interests are in Natural Language Processing and Explainable AI. Some of the areas I wish to work are,

  • Information Extraction, Multilingual and low‐resource NLP, Social Computing [Important (fake, hate, abusive, stance) content classification]
  • Multimodal NLP [utilize linguistic, acoustic, and visual features to build intelligent systems]
  • Explainable AI [explain behind the scenes of the prediction of ML models]

Publications

Works in Progress

BanglaMM-FNX: A Multimodal Framework for Bengali Fake News Classification

Ongoing

Conferences

Journals

Workshops

  1. EACL-2024
    Hate and Offensive Language Detection in Telugu Code-Mixed Text Using Sentence Similarity BERT
    Salman Farsi, Asrarul Hoque Eusha, & Mohammed Moshiul Hoque
    In Proceedings of the Fourth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages (DravidianLangTech-2024)
    [Conference Link] | [Paper] | [Code]
  2. EACL-2024
    Fake News Detection in Malayalam Language Leveraging Fine-Tuned MuRIL BERT
    Salman Farsi, Asrarul Hoque Eusha, Ariful Islam, Hasan Mesbaul Ali Taher, & Mohammed Moshiul Hoque
    In Proceedings of the Fourth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages (DravidianLangTech-2024)
    [Conference Link] | [Paper] | [Code]

    🥇 Top model in fake news detection challenge

  3. EACL-2024
    A Comprehensive Evaluation and Superior Performance of Transformer-Based Models in Hate Speech Event Detection and Stance Classification for Climate Activism
    Salman Farsi, Asrarul Hoque Eusha, & Mohammed Shamsul Arefin
    In Proceedings of the 7th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Text (CASE-2024)
    [Conference Link] | [Paper] | [Code]

    🥇 Top model in hate speech event detection challenge

  4. EACL-2024
    Sentiment Analysis using Transformer-Based Models in Code-Mixed and Transliterated Tamil and Tulu
    Salman Farsi, Asrarul Hoque Eusha, Ariful Islam, & Mohammed Moshiul Hoque
    In Proceedings of the Fourth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages (DravidianLangTech-2024)
    [Conference Link] | [Paper] | [Code]

    🥇 Top model in sentiment analysis challenge