Avatar

Tashin Hossain

Lecturer || NLP Researcher

Hello! I am Tashin Hossain. I am a recent graduate from the Department of Computer Science and Engineering at University of Chittagong, Bangladesh and currently employed as a Lecturer in the Department of of Computer Science and Engineering of Premier University, Chittagong, Bangladesh.

My primary research lies in Natural Language Processing, but it also includes Multimodal Information Processing, Large Language Models, Computational Social Science, and Information Retrieval.

I enjoy outdoor activities cycling, traveling, and watching movies.

Interests

  • Natural Language Processing
  • Multimodal Information Processing
  • Large Language Model
  • Computational Social Science
  • Information Retrieval
  • Opinion Mining

Education

    • Bachelor of Science in Computer Science (2018 - 2023)

      University of Chitagong






Professional Experience

Lecturer

Department of Computer Science and Engieering
Premier University

Adjunct Lecturer

Department of Computer Science and Engieering
International Islamic University Chittagong (IIUC)

Course Instructor of Computer Graphics and Artificial Intelligence

Research Assistant

Data Science Research Group
University of Chittagong






Publications

Leveraging Fusion of Sequence Tagging Models for Toxic Spans Detection

Status : Published on Neurocomputing (Elsevier), Vol.-500, pp. 688-702, 21 August, 2022.

CSECU-DSG at WNUT-2020 Task 2: Exploiting ensemble of transfer learning and hand-crafted features for identification of informative COVID-19 English tweets

Status : W-NUT 2020, pp. 394-398, Nov 19, Online, 2020

CSECU-DSG at SemEval-2021 Task 5: Leveraging Ensemble of Sequence Tagging Models for Toxic Spans Detection

Status : SemEval-2021, pages 990-994, August 5-6, Bangkok, Thailand (online), 2021

CSECU-DSG at SemEval-2021 Task 6: Orchestrating Multimodal Neural Architectures for Identifying Persuasion Techniques in Texts and Images

Status : SemEval-2021, pp. 1088-1095, August 5-6, Bangkok, Thailand (online), 2021

CSECU-DSG at SemEval-2023 Task 6: Segmenting Legal Documents into Rhetorical Roles via Fine-tuned Transformer Architecture

Status : SemEval-2023, pp.-, July 13-14, Toronto, Canada (online), 2023

KingsmanTrio at SemEval-2023 Task 10: Analyzing the Effectiveness of Transfer Learning Models for Explainable Online Sexism Detection

Status : SemEval-2023, pp.-, July 13-14, Toronto, Canada (online), 2023

Teaching

Course Code Course Title Keywords Course Outline
CSE 3635 Artificial Intelligence Concepts of AI, Problem Solving Agent, Searching Techniques, Game Playing, Constraint Satisfaction Problem, Propositional and First Order Logic, Inference in FOL, Proabalistic Reasoning, Expert System, Natural Language Processing
CSE 3636 Artificial Intelligence Lab Prolog, Python, Searching Techniques, Game Playing, Constraint Satisfaction Problem, Natural Language Processing, Linear Regression, Decesion Tree, Perceptron, Expert System
CSE 4741 Computer Graphics Computer Graphics, Modelling, Rendering, Transformation, Viewing, Clipping, Projection, and Hidden Surface
CSE 4742 Computer Graphics Lab Graphics, OpenGL, Modeling, Rendering, Transformation, Viewing, Clipping, Projection
CSE 2415 Algorithms Divide and Conquer, Dynamic Programming, Greedy Algorithms, Backtracking, Branch and Bounds, and Approximation Algorithms
CSE 2416 Algorithms Lab Sorting, Searching, Traversal, Path Finding, Dynamic Programming, Backtracking, Divide and Conquer
CSE 338(V3) Software Development Laravel Framework, Routing, Migration, Controller, Eloquent ORM, Middleware, and Auth



Projects

 
 
 
 
 

Anticipating Ailments Based on Symptoms: A Rule-Based System

Description: I've developed a rule-based expert system trained to recognize 20 distinct diseases with 64 distinct symptoms. It can make predictions based on its extensive knowledge of specific diseases.
Technology Used: Prolog, Kaggle.
[Details]

 
 
 
 
 

Robo-Biz

Description: The Android app is a 3-tier architecture-based platform developed in Java using Android Studio, featuring tutorials, a marketplace for buying and selling robot parts, and a newsfeed for sharing informative robotics news.
Technology Used: Android Studio, Python, Firebase, TensorFlow, Canva.

 
 
 
 
 

Programming Club Website

Description: The web platform for a programming club includes features like member profiles, coach information, contest details, class information, and upcoming onsite and online contest information.
Technology Used: PHP, CSS, HTML, JavaScript and SQL.
[Details]

 
 
 
 
 

Undergraduate Student Helping Website

Description: This is a web application that provides undergraduate students with a forum for undergraduaterelated questions. In addition to a chatbot, this website provides a notification system for tracking various contests, scholarships, seminars, and conferences.
Technology Used: Django, Python, Html, CSS, PostgreSQL

 
 
 
 
 

Medical Information System

Description: The software runs on Android and has a three-tiered structure. It features an appointment scheduler, a report display, and a symptom checker
Technology Used: Android Studio, Python, Firebase, TensorFlow, Canva.




Courses

 
 
 
 
 

Generative AI with Large Language Models

Platform: Coursera
Keywords: LLMs, In-context Learning, Prompt Engineering.
Status: In progress













Awards



















Contact