Saumitra Yadav
Computer Science · Purdue University West Lafayette
Publications
20
Citations
34
Est. group size
~2
Recurring co-author estimate
Active years
8
Publishing since 2019
This researcher's work centers on machine translation for low-resource languages, particularly Indian languages, including techniques like data curation, subword segmentation (byte pair encoding), and grammar error correction. The bibliographic record also shows some unrelated publications in other fields (e.g., fly neuromuscular biology, physical therapy, materials science, photonics), suggesting either name overlap in the data or a mix of collaborations across different disciplines. Prospective students should note the primary and most consistent thread is natural language processing and machine translation methods.
Publication output was sparse or absent in the earlier part of the decade but has grown noticeably since 2022, with a peak in 2024.
Generated by claude-sonnet-5 from public bibliographic data · Jul 20, 2026
- Get away with less: Need of source side data curation to build parallel corpus for low resource Machine Translation
arXiv (Cornell University) · 2026
- Get away with less: Need of source side data curation to build parallel corpus for low resource Machine Translation
arXiv (Cornell University) · 2026
- A3-108 at BHASHA Task1: Asymmetric BPE configuration for Grammar Error Correction
2025
- A Preliminary Exploration of Phrase-Based SMT and Multi-BPE Segmentations through Concatenated Tokenised Corpora for Low-Resource Indian Languages
2025
- Segmentation Beyond Defaults: Asymmetrical Byte Pair Encoding for Optimal Machine Translation Performance
arXiv (Cornell University) · 2025
- CoST of breaking the LLMs
2024
- A3-108 Controlling Token Generation in Low Resource Machine Translation Systems
2024
- Beadex, the <i>Drosophila</i> LIM only protein, is required for the growth of the larval neuromuscular junction
Journal of Neurophysiology · 2024
- Compare the Effect of Functional Training and Complementary Exercise in Patient with Chronic Facial Palsy
International Journal of Research Publication and Reviews · 2024
- Beadex, the <i>Drosophila</i> LIM only protein, is required for the growth of the larval neuromuscular junction and sensorimotor activities
bioRxiv (Cold Spring Harbor Laboratory) · 2023
- A3-108 Machine Translation System for Similar Language Translation Shared Task 2020
2020
- A3-108 Machine Translation System for LoResMT 2019
2019
- High-Speed Cavity Enhanced Silicon Photodetector on SiN-SOI Platform for Short Reach Optical Datacom
2019 Workshop on Recent Advances in Photonics (WRAP) · 2019
- Utilization of Sugarcane Bagasse Ash in Bitumen
2019
- bioRxiv (Cold Spring Harbor Laboratory)×3
- arXiv (Cornell University)×3
- Nature Communications×1
- Science Advances×1
- Cell Reports×1
- Mohammad Javad Hosseini
Computer Science · Purdue University West Lafayette
- Fanyou Wu
Computer Science · Purdue University West Lafayette
- Allen Riddell
Computer Science · Indiana University
- Damir Ćavar
Computer Science · Indiana University
- Elsayed Issa
Computer Science · Purdue University West Lafayette
This profile was generated automatically from public scholarly data (OpenAlex). Group size and activity levels are estimates derived from co-authorship patterns.
Last updated Jul 20, 2026.
Claim or correct this profile