Papers by Tirthankar Dasgupta
Learning Domain Terms - Empirical Methods to Enhance Enterprise Text Analytics Performance (2020.coling-industry)
Copied to clipboard
| Challenge: | Standard text analytics algorithms are degraded on consumer generated data, a study finds . enterprise data contains domain terms that are not available in general purpose thesaurus . |
| Approach: | They propose unsupervised methods for cleaning noisy repositories after domain terms are segregated from true noise terms. |
| Outcome: | The proposed method improves classification accuracy after noise correction . it is based on a systematic analysis of enterprise data . |
Predicting ICU Length of Stay for Patients using Latent Categorization of Health Conditions (2025.naacl-industry)
Copied to clipboard
| Challenge: | Traditional approaches to predicting the duration of a patient's stay in an Intensive Care Unit (ICU) rely on structured clinical data, but recent advances in language models offer significant potential to utilize unstructured text data for ICU length-of-stay (LoS) predictions. |
| Approach: | They propose a method for analyzing nursing notes to predict ICU length-of-stay of patients. |
| Outcome: | The proposed model outperforms baseline models on the MIMIC-III dataset and shows that it significantly outperformed existing models. |
DisGraph-RP: Graph-Augmented Temporal Modeling with Aspect-Based Contrastive Encoding of Discharge Summary for Readmission Prediction (2026.eacl-industry)
Copied to clipboard
| Challenge: | Recent data indicate that nearly 15% of hospitalized patients in the U.S. are readmitted soon after discharge. |
| Approach: | They propose a graph-augmented temporal modeling framework that integrates structured discourse-aware text representation with cross-admission relational reasoning. |
| Outcome: | The proposed model improves on baseline models and prompting-based models on real-world datasets. |
RegNLI: Detecting Online Product Misbranding through Legal and Linguistic Alignment (2026.eacl-industry)
Copied to clipboard
| Challenge: | Existing approaches to claim verification focus on keyword matching or generic text classification . misbranding involves deceptive labeling or advertising that misleads consumers about a product's nature or quality . |
| Approach: | They propose a framework that formulates misbranding detection as an inference task between product claims and regulatory provisions. |
| Outcome: | The proposed framework outperforms baselines in misbranding detection and regulation alignment metrics. |
Automatic Curation and Visualization of Crime Related Information from Incrementally Crawled Multi-source News Reports (C18-2)
Copied to clipboard
| Challenge: | Existing methods for curation of crime-related information from digitally published News articles are not limited to detecting known crimes but contribute actively towards maintaining an updated crime ontology. |
| Approach: | They propose a system for automatic curation of crime-related information from multi-source digitally published News articles. |
| Outcome: | The proposed system extracts crime related entities and events from 5000 crime-reporting News articles span over time and multiple sources. |