Mausam Jain

I am a Senior Research Scientist at Rakuten Institute of Technology, Rakuten Inc. where my current area of research is in Recommender Systems and Model Explainability for Deep Learning Models. My previous work on Natural Language Processing involves understanding of dual-encoder retrieval models and their ranking interpretation. I am interested in exploring reasoning abilities of and embeddings learnt by multilingual and multimodal (large) language models and their interpretability. Otherwise, I love table tennis and video games! And learning the unlearnt concepts.
I completed my Master's in Computer Science from Indian Institute of Technology Hyderabad in 2017, where I was advised by Dr. Vineeth N Balasubramanian, for on my thesis on Learning Graph invariant Hierarchical Representations for sub-graph matching and classification.

Publications

Debopriyo Banerjee, Mausam Jain, and Ashish Kulkarni. MFBE: Leveraging multi-field information of FAQs for efficient dense retrieval. In Advances in Knowledge Discovery and Data Mining: 27th Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD 2023, Proceedings, Part III, 2023.
Raymond Hendy Susanto, Dongzhe Wang, Sunil Yadav, Mausam Jain, and Ohnmar Htun. Rakuten‘s participation in WAT 2021: Examining the effectiveness of pre-trained models for multilingual and multimodal machine translation. In Proceedings of the 8th Workshop on Asian Translation, WAT2021. Association for Computational Linguistics.
Mausam Jain. Learning hierarchical representations of graphs using neural network techniques. Master’s thesis, Indian Institute of Technology Hyderabad, 2017.

Patents

Information Processing Device and Method - prediction of internal greenhouse environment and minimization of sensor installation and maintenance cost using machine learning.
Learning System and Method for Text Similarity - novel technique to perform the FAQ retrieval given user query as input.