Yatin Chaudhary

Continual Learning | Federated Learning | Representation Learning

Natural Language Processing | Deep Learning

CURRENT AFFILIATIONS

PhD Student @ CIS, LMU
Applied AI-NLP Scientist @ DRIMCo GmbH

EMAIL

firstname.lastname@drimco.net

Yatin Chaudhary

I am a PhD student at the Center for Information and Language Processing (CIS) at the Ludwig Maximilian University of Munich (LMU). I am also currently working (full-time) as an Applied AI-NLP Scientist at DRIMCo GmbH, Munich in the area of Natural Language Processing (NLP). I am co-supervised by Prof. Dr. Hinrich Schütze, CIS, LMU and Dr. Pankaj Gupta, DRIMCO GmbH. I completed my Master's thesis under the co-supervision of Prof. Dr. Thomas Runkler and Dr. Pankaj Gupta at Machine Intelligence (MIC), Siemens Corporate Technology. My research focuses on developing Representation Learning methods/algorithms (extending to Continual/Lifelong Learning and Federated Learning paradigms) using deep neural topic and language models for natural language text understanding under high and low-resource data settings. I work on research as well as applied projects and one of the research goals is the "easy integration and effective results" in AI-based products.

EDUCATIONAL BACKGROUND

Doctor of Philosophy (Ph.D.) Student in Computational Linguistics @ Ludwig Maximilian University (LMU), Munich (Germany)
Master of Science (M.Sc.) in Computational Science and Engineering @ Technical University Munich (TUM), Munich (Germany)
Bachelor of Technology (B.Tech.) in Mechanical Engineering @ Indian Institute of Technology Jodhpur (IITJ), Jodhpur (India)

PUBLICATIONS

Title: Federated Continual Learning for Text Classification via Selective Inter-client Transfer

Authors: Yatin Chaudhary, Pranav Rai, Matthias Schubert, Hinrich Schütze, Pankaj Gupta

Venue: Published as a conference paper EMNLP 2022 | [Paper] [Code]

Title: Multi-source Neural Topic Modeling in Multi-view Embedding Spaces

Authors: *Pankaj Gupta, *Yatin Chaudhary, Hinrich Schütze

Venue: Published as a conference paper NAACL 2021 | [Paper] [Code]

Title: TopicBERT for Energy Efficient Document Classification

Authors: *Yatin Chaudhary, *Pankaj Gupta, Khushbu Saxena, Vivek Kulkarni, Thomas Runkler, Hinrich Schütze

Venue: Published as a conference paper at EMNLP 2020 | [Paper] [Code]

Title: Explainable and Discourse Topic-aware Neural Language Understanding

Authors: Yatin Chaudhary, Hinrich Schütze, Pankaj Gupta

Venue: Published as a conference paper at ICML 2020 | [Paper] [Code]

Title: Neural Topic Modeling with Continual Lifelong Learning

Authors: Pankaj Gupta, Yatin Chaudhary, Hinrich Schütze

Venue: Published as a conference paper at ICML 2020 | [Paper] [Code]

Title: Lifelong Neural Topic Learning in Contextualized Autoregressive Topic Models of Language via Informative Transfers

Authors: Yatin Chaudhary, Pankaj Gupta, Thomas Runkler

Venue: Master's Thesis (Technical University Munich) 2019 | [Thesis]

Title: BioNLP-OST 2019 RDoC Tasks: Multi-grain Neural Relevance Ranking Using Topics and Attention Based Query-Document-Sentence Interactions

Authors: *Yatin Chaudhary, *Pankaj Gupta, Hinrich Schütze

Venue: Published as a workshop paper at EMNLP-IJCNLP 2019 | [Paper] [Code]

Title: textTOvec: Deep Contextualized Neural Autoregressive Topic Models of Language with Distributed Compositional Prior

Authors: Pankaj Gupta, Yatin Chaudhary, Florian Buettner, Hinrich Schütze

Venue: Published as a conference paper at ICLR 2019 | [Paper] [Code]

Title: Document Informed Neural Autoregressive Topic Models with Distributional Prior

Authors: Pankaj Gupta, Yatin Chaudhary, Florian Buettner, Hinrich Schütze

Venue: Published as a conference paper at AAAI 2019 | [Paper] [Code]

Page updated

Google Sites

Report abuse