Niraj Pahari
Ph.D. student @ Kyushu Institute of Technology | [email protected]

I am a Ph.D. student of Shimada Laboratory in the Department of Artificial Intelligence at Kyushu Institute of Technology (Kyutech), Fukuoka, Japan, conducting research in Natural Language Processing advised by Prof. Kazutaka SHIMADA. Prior to this, I did my masters in RAI lab at KMITL in Bangkok, Thailand.

My current research interests lie in active learning and multi-task learning in code-mixed data.

  |     |     |  


Education

Oct. 2021 - Present
Kyushu Institute of Technology (Kyutech)
Ph.D. Student in Department of Artificial Intelligence
Aug. 2019 - July 2021
King Mongkut's Institute of Technology Ladkrabang (KMITL)
Masters of Engineering in Robotics and Computational Intelligence Systems
  • Masters Thesis: Paraphrase Identification Using Features From Word and Sentence Level Embedding

Experience

Jan 2021 - Apr 2022
KMITL Robotics and AI Laboratory
Full Stack Web Developer
  • Full stack web application for Department of Disease Control, Thailand.
Apr 2020 - Aug 2020
KMITL Robotics and AI Laboratory
ROS Developer
  • ROS MoveIt! for interfacing ABB IRB 1100 industrial robot with web application for KRAI platform.
Jan 2020 - Mar 2022
King Mongkut's Institute of Technology
Lab Instructor
  • Laboratory course instructor for Industrial Robotics, Mobile Robotics, Python with Image Classification and Programming in C.
July 2016 - July 2019
Soch College of IT, Pokhara, Nepal
Part-Time Lecturer
  • Theory and practical sessions for undergraduate level courses: DBMS, Advanced-DBMS, AI, and Data Mining and Data Warehousing
Jan 2015 - July 2019
Genese Solution Pvt. Ltd.
Backend Developer
  • Application development for various clients. Held the responsibility of working with various teams remotely and understanding the requirements of the client and act accordingly.

Research

Journal/International Conference

Share What You Already Know: Cross-Language-Script Transfer and Alignment for Sentiment Detection in Code-Mixed Data
Niraj Pahari, Kazutaka Shimada
ACM Trans. Asian Low-Resour. Lang. Inf. Process.
[Paper] [Bibtex]
Layer Configurations of BERT for Multitask Learning and Data Augmentation
Niraj Pahari, Kazutaka Shimada
Journal of Advanced Computational Intelligence and Intelligent Informatics
[Paper] [Bibtex]
Language Preference for Expression of Sentiment for Nepali-English Bilingual Speakers on Social Media
Niraj Pahari, Kazutaka Shimada
Sixth Workshop on Computational Approaches to Linguistic Code-Switching (CALCS-EMNLP2023 Workshop)
[Paper] [Bibtex]
Multilingual Symptom Prediction by Simultaneous Learning using BERT
Chencheng Zhu, , Niraj Pahari, Kazutaka Shimada
2023 International Conference on Asian Language Processing
[Paper] [Bibtex]
Handling data scarcity in code-mixing using learning-based approaches
Niraj Pahari, Kazutaka Shimada
2023 14th IIAI International Congress on Advanced Applied Informatics (IIAI-AAI)
[Paper] [Bibtex]
Multi-Task Learning Using BERT With Soft Parameter Sharing Between Layers
Niraj Pahari, Kazutaka Shimada
2022 Joint 12th International Conference on Soft Computing and Intelligent Systems and 23rd International Symposium on Advanced Intelligent Systems (SCIS&ISIS)
[Paper] [Bibtex]
Semantic Similarity calculation using the features from pre-trained vector and sentence level embedding
Niraj Pahari, Somyot Kaitwanidvilai
ICAST 2021
[Paper] [

Pdf Password: iceast2021

] [Bibtex]
Utilizing User Generated Contents to Describe Tourism Areas of Interest
Bidur Devkota, Hiroyuki Miyazaki, Niraj Pahari
2019 First International Conference on Smart Technology & Urban Development
[Paper] [Bibtex]

Research Groups

Character-level Data Augmentation on Code Mixed Sentences for Low-Resource Settings
Niraj Pahari, Kazutaka Shimada
言語処理学会第29回年次大会(NLP2023) / The 29th Annual Conference of the Association for Natural Language Processing (NLP2023)
[Paper] [Bibtex]
BERTを用いた多言語同時学習による疾患分類
朱晨成, Niraj Pahari, 嶋田和孝
言語処理学会第29回年次大会(NLP2023) / The 29th Annual Conference of the Association for Natural Language Processing (NLP2023)
[Paper] [Bibtex]

Templete taken from Anastasis Stathopoulos, Jon Barron, and Georgia Gkioxari