About
I'm a second year PhD student at the Center for Language and Speech Processing at Johns Hopkins University, advised by Professor David Yarowsky. In the past, I worked at ALMAnaCH, INRIA in Paris with Benoît Sagot and Rachel Bawden. Even before that, I graduated from the EMLCT Masters' program as an Erasmus scholar, with a dual MSc. in Computational Linguistics at Charles University, Prague (first year), and Language and Science Technologies at Saarland University, Germany (second year). I'm interested in building NLP tools for text and speech that are available for all the world's languages in their dialectal, colloquial, and code-switched variants :)
Publications
See ACL Anthology or Google Scholar.
-
Niyati Bafna, Emily Chang, Nathaniel R. Robinson, David R. Mortensen, Kenton Murray, David Yarowsky, and Hale Sirin. 2025. DialUp! Modeling the Language Continuum by Adapting Models to Dialects and Dialects to Models. .
-
Niyati Bafna, Kenton Murray, and David Yarowsky. 2024. Evaluating Large Language Models along Dimensions of Language Variation: A Systematik Invesdigatiom uv Cross-lingual Generalization. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 18742–18762, Miami, Florida, USA. Association for Computational Linguistics.
-
Niyati Bafna, Philipp Koehn, and David Yarowsky. 2024. Pointer-Generator Networks for Low-Resource Machine Translation: Don’t Copy That! In Proceedings of the Fifth Workshop on Insights from Negative Results in NLP, pages 60–72.
Niyati Bafna, Cristina España-Bonet, Josef van Genabith, Benoît Sagot, and Rachel Bawden. 2024. When Your Cousin Has the Right Connections: Unsupervised Bilingual Lexicon Induction for Related Data-Imbalanced Languages. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 17544–17556, Torino, Italia. ELRA and ICCL.
Niyati Bafna, Cristina España-Bonet, Josef van Genabith, Benoît Sagot, and Rachel Bawden. 2023. Cross-Lingual Strategies for Low-Resource Language Modeling: A Study on Five Indic Dialects. In Proceedings of the 18th Conference on Traitement Automatique des Language Naturelles. Paris, France. TALN.
Niyati Bafna, Josef van Genabith, Cristina España-Bonet, and Zdeněk Žabokrtský. 2022. Combining Noisy Semantic Signals with Orthographic Cues: Cognate Induction for the Indic Dialect Continuum. In Proceedings of the 26th Conference on Computational Natural Language Learning, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Niyati Bafna and Zdeněk Žabokrtský. 2022. Subword-based Cross-lingual Transfer of Embeddings from Hindi to Marathi and Nepali. In Proceedings of the 19th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 61–71, Seattle, Washington. Association for Computational Linguistics.
Kartik Sharma, Niyati Bafna, and Samar Husain. 2021. Clause Final Verb Prediction in Hindi: Evidence for Noisy Channel Model of Communication. In Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics, pages 160–170, Online. Association for Computational Linguistics.
Zdeněk Žabokrtský, Niyati Bafna, Jan Bodnár, Lukáš Kyjánek, Emil Svoboda, Magda Ševčíková, and Jonáš Vidra. 2022. Towards Universal Segmentations: UniSegments 1.0. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 1137–1149, Marseille, France. European Language Resources Association.
Niyati Bafna, Martin Vastlik, and Ondrej Bojar. 2021. Constrained Decoding for Technical Term Retention in English-Hindi MT. In Proceedings of the 18th International Conference on Natural Language Processing, pages 1–6, National Institute of Technology Silchar, India. NLP Association of India.
Niyati Bafna and Dipti Sharma. 2019. Towards Handling Verb Phrase Ellipsis in English-Hindi Machine Translation. In Proceedings of the 16th International Conference on Natural Language Processing, pages 150–159, International Institute of Information Technology, Hyderabad, India. NLP Association of India.
News
Feb 2025 Check out our new technique for inducing dialectal robustness in pretrained models DialUp! Modeling the Language Continuum by Adapting Models to Dialects and Dialects to Models .
Nov 2024 Accepted a internship offer from Meta to work with their multilinguality team next summer.
Sept 2024 New paper accepted to EMNLP '24: Evaluating Large Language Models along Dimensions of Language Variation: A Systematik Invesdigatiom uv Cross-lingual Generalization . See you in Miami :-)
May 2024 Our work on Unsupervised Bilingual Lexicon Induction for Related Data-Imbalanced Languages won the COLING Best Student Paper Award at LREC-COLING!
Feb 2024 I'll be interning at Seamless Meta in Menlo Park over the summer.
June 2023 Presented my work, called Cross-Lingual Strategies for Low-Resource Language Modeling: A Study on Five Indic Dialects, at TALN 2023, Paris, France. It's about comparing basic multilingual strategies for language modelling, for truly low-resource languages that belong to the same dialect continuum or language family.
April 2023 Accepted my PhD offer at JHU CSLP, and will be starting in Fall 2023. I'll be advised by Professor David Yarowsky.
Oct 2022 Invited talk at Linguistic Mondays, Institute of Formal and Applied Linguistics, Charles University, on two of my recent works in experiments on Indic languages: Empirical Models for an Indic Dialect Continuum
Oct 2022 New paper accepted at CoNLL 2022! This paper was adapted from my M.Sc. thesis; it is about data collection for 26 dialects and languages of the Indic language continuum, along with strategies for cognate induction for these languages as a step towards building bilingual resources for (extremely) low resouce languages.
Oct 2022 Starting as a research engineer at ALMAnaCH, INRIA in Paris, with Benoît Sagot and Rachel Bawden; super excited :)
Aug 2022 Defended my thesis (twice), graduated from Charles University and Saarland University! I did my thesis jointly with the MLT group at DFKI and UFAL. I was supervised by Prof. Josef van Genabith and Cristina España-Bonet from the former and Zdeněk Žabokrtský from the latter. The thesis is about cognate induction and data collection for 26 (extremely) low resourced languages of the Indic dialect continuum; check it out here: Empirical Models for an Indic Language Continuum!
Jul 2022 New paper at SIGMORPHON@NAACL '22, about subword level embeddings transfer from Hindi to Marathi and Nepali.
Apr 2022 New paper at LREC '22 (the UniSegements project) with UFAL, harmonizing different morphological resources for 17 languages. I worked on Hindi, Marathi, Malayalam, Tamil, and Bengali.
Dec 2021 New paper at ICON '21, NIT Silchar, about constrained deconding for technical terms in English-Hindi MT with UFAL.
Apr 2022 New paper at CMCL@NAACL '21 with Prof. Samar Husain at IIT Delhi, India, about computational modelling of cognitive hypotheses, specifically, the adaptability hypothesis and noisy channel hypothesis.
Oct 2020 Started at the EMLCT Masters' program with an Erasmus scholarship.
May 2020 Graduated with a bachelors' degree from Ashoka University :-)
Dec 2019 New paper at ICON 19, IIIT Hyderabad, with Prof. Dipti Misra Sharma at LTRC, about verb phrase ellipsis handling in English-Hindi MT.
CV
Here's a PDF version of all of this stuff.
Research Interests
I'm interested in mid- to low-resource settings and domain generalization for multilingual and dialectal natural language understanding, generation, machine translation, ASR, and LID. I'm also interested in benchmarking core linguistic capabilities in large language models in a robust and interpretable manner. Here are some of the kinds of problems in this space.
Cross-lingual transfer...: Many dialects and languages of the world exist across a continuum, with varying degrees of resourcedness at various points. Can we model this continuum in a manner that can help NLP tools "fill in the gaps"? How can we most effectively use its properties to leverage good datasets and models at certain points on this continuum for others?
...and the limits of cross-lingual transfer: Many things about linguistic divergence are systematic, meaning that models can extrapolate performance to low-resource languages that are close enough to high-resource languages in regular ways. However, languages also have irregular, language-specific phenomena. Can we theoretically quantify the limits of cross-lingual transfer for a given language family? Can we identify the kinds of phenomena that cannot be transferred, so that we can evolve targeted solutions for them?
Tool use for multilinguality: LLMs are still often bad at comprehension and generation for several mid- to low-resource languages. For these languages, we may want to leverage the reasoning capabilities of LLMs but outsource linguistic processing and generation to specialized modules. What are the best architectural and training strategies for these modules and their integration with the LLM pipeline?
ASR, speech representations: Speech tokenization matters! Do hidden unit representations need to be phonologically sensible to generalize multilingually? I'm also interested in domain generalization for ASR (example scenario: we have good general ASR, and we want to use it for a meeting about something niche, like, bioluminescence in Photinus pyralis. We have a lexicon containing words we might expect. How can we best feed such priors into the model at test time?)
For Fun...
When I'm not working, I enjoy playing tennis, solving cryptic crosswords, reading about politics/history, writing, salsa and bachata dancing, and learning languages! I also enjoy the occasional game of rapid chess, and am a fan of the Sicilian Dragon.
*And* I have a lifelong desire to sing acapella but have never actually tried it.