Papers by Sonja Schmer-Galunder
Recognizing Value Resonance with Resonance-Tuned RoBERTa Task Definition, Experimental Validation, and Robust Modeling (2024.lrec-main)
Copied to clipboard
Noam K. Benkler, Scott Friedman, Sonja Schmer-Galunder, Drisana Marissa Mosaphir, Robert P. Goldman, Ruta Wheelock, Vasanth Sarathy, Pavan Kantharaju, Matthew D. McLure
| Challenge: | Understanding the implicit values and beliefs of diverse groups and cultures using qualitative texts is a fundamental goal of social anthropology. |
| Approach: | They propose to use a novel hand-annotated dataset and a transformer-based model to model the NLP task of Recognizing Value Resonance (RVR) they extend existing work by refining the task definition and releasing the WVC dataset. |
| Outcome: | The proposed models outperform top-performing Recognizing Textual Entailment models in recognizing value resonance and zero-shot GPT-3.5 under several different prompt structures, emphasizing its practical applicability. |
From Stance to Concern: Adaptation of Propositional Analysis to New Tasks and Domains (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing paradigms for propositional analysis use stances and concerns to generate explanatory representations. |
| Approach: | They propose a generalized paradigm for adaptation of propositional analysis to new tasks and domains by using an analogy between stances and concerns. |
| Outcome: | The proposed model yields 231% improvement in recall over baseline, with only 10% loss in precision. |