Papers by Allan Hanbury
AustroTox: A Dataset for Target-Based Austrian German Offensive Language Detection (2024.findings-acl)
Copied to clipboard
| Challenge: | Scholars call for more personalized mechanisms of content moderation to account for multifaceted differences. |
| Approach: | They propose to annotate a news forum's user comments with a German dialect and identify their spans as vulgar language or offensive statements. |
| Outcome: | The proposed model interpretability improves on fine-tuned Transformer models and large language models in a zero-shot fashion. |
Medical Entity Corpus with PICO elements and Sentiment Analysis (L18-1)
Copied to clipboard
| Challenge: | In this paper, we establish a PICO and a sentiment annotated corpus of clinical trial publications. |
| Approach: | They propose to create a phrase-level PICO corpus and a sentence-level sentiment annotated corpus from clinical trial publications. |
| Outcome: | The proposed corpus is annotated on a phrase-level and a sentiment annotation on the same corpus. |
Effective Crowd-Annotation of Participants, Interventions, and Outcomes in the Text of Clinical Trial Reports (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Evidence Based medicine searches for Participants, Interventions, and Outcomes (PIO) in clinical trial reports requires high-quality corpora. |
| Approach: | They propose to use a crowd-annotated approach to search for PIOs in clinical trial reports to compensate for the lack of domain-specific expertise of crowdworkers by using similar sentences already annotated by experts. |
| Outcome: | The proposed approach outperforms the Baseline approach and the crowd-annotated approach with similar sentences for each task-instance example. |