Nafis Sadeq
5 papers · 2019–2024 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
🌉 Interdisciplinary Bridge · Bronze 🏃 Academic Marathon · Sprint 🗺️ Taxonomy Completionist (18) 🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Bronze
🌱
Topic Pioneer
🧭
Keyword Pioneer
Top co-authors
Research topics
Machine Learning
(4)
Natural Language Processing
(4)
Learning Types · Machine Learning
(3)
Deep Learning
(2)
Applications
(2)
Core Methods
(2)
Generation
(2)
Learning Types · Deep Learning
(2)
Resources & Methods
(2)
Artificial Intelligence
(1)
Speech & Audio
(1)
Application Areas
(1)
Core AI
(1)
Synthesis
(1)
Techniques
(1)
Keywords
masked language modeling
(2)
unsupervised learning
(2)
unsupervised pretraining
(1)
self-supervised learning
(1)
speech recognition
(1)
question answering
(1)
factual knowledge
(1)
automatic speech recognition
(1)
semi-supervised training
(1)
pointwise mutual information
(1)
hallucination mitigation
(1)
knowledge-intensive task
(1)
data-driven approach
(1)
grapheme-to-phoneme conversion
(1)
end-to-end model
(1)
word error rate
(1)
language model pretraining
(1)
factual recall
(1)
parametric knowledge
(1)
adversarial evaluation
(1)
Papers
Mitigating Hallucination in Fictional Character Role-Play
EMNLP 2024
Unsupervised Improvement of Factual Knowledge in Language Models
EACL 2023
InforMask: Unsupervised Informative Masking for Language Model Pretraining
EMNLP 2022
Improving End-to-End Bangla Speech Recognition with Semi-supervised Training
EMNLP 2020
Customizing Grapheme-to-Phoneme System for Non-Trivial Transcription Problems in Bangla Language
NAACL 2019