Papers by Avijit Mitra
Synth-SBDH: A Synthetic Dataset of Social and Behavioral Determinants of Health for Clinical Text (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing SBDH datasets lack detailed annotations and are limited in their availability and coverage. |
| Approach: | They propose a synthetic SBDH annotation dataset with detailed SBDH status, temporal information, and rationale across 15 categories. |
| Outcome: | The proposed dataset outperforms models with no Synth-SBDH training on three tasks using real-world clinical datasets from two distinct hospital settings. |
Generating Contextual Images for Long-Form Text (2024.lrec-main)
Copied to clipboard
| Challenge: | Recent advances in Text-to-Image models require short prompts that describe both the content and style of the target image. |
| Approach: | They propose to use Large Language Models (LLMs) and Text-to-Image Models to synthesize relevant visual imagery from generic long-form text. |
| Outcome: | The proposed models can generate high-quality images from short prompts that describe both the content and style of the target image. |
Knowledge Injected Prompt Based Fine-tuning for Multi-label Few-shot ICD Coding (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for ICD coding are limited due to the high-dimensional space of multi-label assignment and the long-tail challenge. |
| Approach: | They propose a prompt-based fine-tuning technique with label semantics to solve this challenge. |
| Outcome: | The proposed method outperforms state-of-the-art methods on a benchmark dataset of code assignment in 14.5% of cases. |