Papers by Jaromir Savelka
Semantic Span Annotation: An Exploratory Study of LLM Annotation (2026.acl-srw)
Copied to clipboard
| Challenge: | Structured span extraction research is siloed by context length, annotation task, and domain . Identifying a span within a natural language text and affixing it with a semantic label has been considered a core task in NLP . |
| Approach: | They propose a framework for structured span annotation that integrates five datasets under a common JSONL format with character-level offsets. |
| Outcome: | The proposed framework can generalize across four domains under three prompting configurations. |
Discovering Explanatory Sentences in Legal Case Decisions Using Pre-trained Language Models (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Understanding written laws is difficult because the abstract rules must account for a variety of situations, even those not yet encountered. |
| Approach: | They constructed a dataset of 26,959 sentences and labeled them in terms of their usefulness for explaining selected legal concepts. |
| Outcome: | The proposed models outperform the prior approaches and can learn surprisingly sophisticated features. |