Papers by Jinho Choi
FedTherapist: Mental Health Monitoring with User-Generated Linguistic Expressions on Smartphones via Federated Learning (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing passive mental health monitoring systems use alternative features such as activity, app usage, and location via smartphones due to data privacy concerns. |
| Approach: | They propose a mobile mental health monitoring system that utilizes continuous speech and keyboard input in a privacy-preserving way via federated learning. |
| Outcome: | The proposed system achieves 0.15 AUROC improvement and 8.21% MAE reduction in self-reported depression, stress, anxiety, and mood from 46 participants. |
Identifying Factual Inconsistencies in Summaries: Grounding LLM Inference via Task Taxonomy (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies have focused on specialized BERT-variants and recent LLMs to reason inconsistencies. |
| Approach: | They propose to incorporate task-specific taxonomy into inferences to facilitate both zero-shot and supervised paradigms. |
| Outcome: | The proposed model outperforms specialized non-LLM and recent LLM models in a number of domains. |
Modeling Task Interactions in Document-Level Joint Entity and Relation Extraction (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing work on document-level relation extraction has focused on end-to-end setting that extracts global entities and relations jointly. |
| Approach: | They propose to introduce a two-way interaction between COREF and RE that is specifically designed to leverage task characteristics, bridging decisions of two tasks for direct task interference. |
| Outcome: | The proposed model achieves the best performance by up to 2.3/5.1 F1 over the baseline. |
SCALE: Upscaled Continual Learning of Large Language Models (2026.findings-acl)
Copied to clipboard
Jin-woo Lee, Junhwa Choi, Bongkyu Hwang, Jinho Choo, Bogun Kim, Jeongseon Yi, Joonseok Lee, DongYoung Jung, Jaeseon Park, Kyoungwon Park, Suk-hoon Jung
| Challenge: | Recent discussions suggest that further progress will come from scaling the right structure, not merely parameters or data, while preserving acquired knowledge. |
| Approach: | They propose a width upscaling architecture that inserts lightweight expansions into linear modules while freezing all pre-trained parameters. |
| Outcome: | The proposed architecture reduces severe forgetting while learning new knowledge on a controlled synthetic biography benchmark. |
Diverse and Effective Synthetic Data Generation for Adaptable Zero-Shot Dialogue State Tracking (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing zero-shot dialogue state tracking datasets are limited in the number of domains and slot types they cover due to the high costs of data collection. |
| Approach: | They propose a fully automatic approach that generates synthetic zero-shot dialogue state tracking datasets. |
| Outcome: | The proposed approach can generate dialogues across 1,000+ domains with silver-standard dialogue state annotations and slot descriptions. |