Scholar
Niyati Bafna
Google Scholar ID: 22sfVrEAAAAJ
Johns Hopkins University, Center for Language and Speech Processing
Low-resource NLP
Large Language Modelling
Machine Translation
Bilingual Lexicon Induction
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
41
H-index
4
i10-index
1
Publications
17
Co-authors
8
list available
Contact
Email
niyatibafna13@gmail.com
CV
Open ↗
GitHub
Open ↗
LinkedIn
Open ↗
Publications
8 items
Rashid: A Cipher-Based Framework for Exploring In-Context Language Learning
2026
Cited
0
Omnilingual MT: Machine Translation for 1,600 Languages
2026
Cited
0
ChiKhaPo: A Large-Scale Multilingual Benchmark for Evaluating Lexical Comprehension and Generation in Large Language Models
2025
Cited
0
How Important is `Perfect' English for Machine Translation Prompts?
2025
Cited
0
The Translation Barrier Hypothesis: Multilingual Generation with Large Language Models Suffers from Implicit Translation Failure
2025
Cited
0
LID Models are Actually Accent Classifiers: Implications and Solutions for LID on Accented Speech
2025
Cited
0
DialUp! Modeling the Language Continuum by Adapting Models to Dialects and Dialects to Models
2025
Cited
0
Evaluating Large Language Models along Dimensions of Language Variation: A Systematik Invesdigatiom uv Cross-lingual Generalization
Conference on Empirical Methods in Natural Language Processing · 2024
Cited
1
Resume (English only)
Academic Achievements
Published multiple papers in top-tier conferences including ACL, EMNLP, Interspeech, COLING, LREC, CoNLL, SIGMORPHON, etc.
Notable papers: 'The Translation Barrier Hypothesis: Multilingual Generation with Large Language Models Suffers from Implicit Translation Failure'
'LID Models are Actually Accent Classifiers: Implications and Solutions for LID on Accented Speech' (Interspeech 2025)
'DialUp! Modeling the Language Continuum by Adapting Models to Dialects and Dialects to Models' (ACL 2025)
'Evaluating Large Language Models along Dimensions of Language Variation' (EMNLP 2024)
'Pointer-Generator Networks for Low-Resource Machine Translation: Don’t Copy That!' (2024)
'When Your Cousin Has the Right Connections: Unsupervised Bilingual Lexicon Induction for Related Data-Imbalanced Languages' (LREC-COLING 2024)
'Cross-Lingual Strategies for Low-Resource Language Modeling: A Study on Five Indic Dialects' (TALN 2023)
'Combining Noisy Semantic Signals with Orthographic Cues: Cognate Induction for the Indic Dialect Continuum' (CoNLL 2022)
'Subword-based Cross-lingual Transfer of Embeddings from Hindi to Marathi and Nepali' (SIGMORPHON 2022)
'Clause Final Verb Prediction in Hindi: Evidence for Noisy Channel Model of Communication' (CMCL 2021)
Co-authors
8 total
Josef van Genabith
DFKI German Research Center for Artificial Intelligence, Saarland University
Kenton Murray
Research Scientist, Johns Hopkins
Zdenek Zabokrtsky
Charles University in Prague
David Yarowsky
Professor of Computer Science, Johns Hopkins University
Rachel Bawden
Inria
Benoît Sagot
Directeur de recherches at Inria, head of the ALMAnaCH team
Co-author 7
Ondřej Bojar
Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up