Deepak Kumar

Orcid: 0000-0002-4828-8328

Affiliations:
  • Johannes Kepler University of Linz, Linz, Austria
  • National Institute of Science Education and Research, Bhubaneswar, Orissa, India (former)


According to our database1, Deepak Kumar authored at least 9 papers between 2021 and 2026.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2026
How Far Can Pretrained LLMs Go in Symbolic Music? Controlled Comparisons of Supervised and Preference-based Adaptation.
CoRR, January, 2026

2024
Fairness of recommender systems in the recruitment domain: an analysis from technical and legal perspectives.
Frontiers Big Data, 2024

Modular Debiasing of Latent User Representations in Prototype-Based Recommender Systems.
Proceedings of the Machine Learning and Knowledge Discovery in Databases. Research Track, 2024

2023
Identifying Words in Job Advertisements Responsible for Gender Bias in Candidate Ranking Systems via Counterfactual Learning.
Proceedings of the 3rd Workshop on Recommender Systems for Human Resources (RecSys in HR 2023) co-located with the 17th ACM Conference on Recommender Systems (RecSys 2023), 2023

Parameter-efficient Modularised Bias Mitigation via AdapterFusion.
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, 2023

Modular and On-demand Bias Mitigation with Attribute-Removal Subnetworks.
Proceedings of the Findings of the Association for Computational Linguistics: ACL 2023, 2023

2022
Dict-NMT: Bilingual Dictionary based NMT for Extremely Low Resource Languages.
CoRR, 2022

2021
NLP@NISER: Classification of COVID19 tweets containing symptoms.
Proceedings of the Sixth Social Media Mining for Health Workshop and Shared Task, 2021

QUARC: Quaternion Multi-Modal Fusion Architecture For Hate Speech Classification.
Proceedings of the IEEE International Conference on Big Data and Smart Computing, 2021


  Loading...