Papers with uncertainty reduction
Foreseeing the Benefits of Incidental Supervision (2021.emnlp-main)
Copied to clipboard
| Challenge: | Real-world applications often require improved models by leveraging a range of cheap incidental supervision signals. |
| Approach: | They propose a unified PAC-Bayesian motivated informativeness measure that characterizes the uncertainty reduction provided by incidental supervision signals. |
| Outcome: | The proposed measure quantifies the value added by incidental supervision signals to sequence tagging tasks. |
Modelling Suspense in Short Stories as Uncertainty Reduction over Neural Representation (2020.acl-main)
Copied to clipboard
| Challenge: | Existing studies on suspense have only sporadically been used in story generation systems. |
| Approach: | They propose a hierarchical language model that computes surprise and uncertainty reduction over story representations and annotated short stories. |
| Outcome: | The proposed model can predict suspense over story representations or probability distributions, and predicts suspensity in movie synopses. |
Boundary-Aware LLM Augmentation for Low-Resource Event Argument Extraction (2026.eacl-long)
Copied to clipboard
| Challenge: | Event argument extraction (EAE) is a crucial task in information extraction but its performance heavily depends on expensive annotated data. |
| Approach: | They investigate argument replacement, adjunction rewriting, their combination, and annotation generation using four LLM-based augmentation strategies. |
| Outcome: | The proposed methods improve performance over boundary-agnostic methods and provide detailed analysis of quality from multiple perspectives. |