Abstract
We describe the ULFRI system used in the Subtask 1 of SemEval-2022 Task 4 Patronizing and condescending language detection. Our models are based on the RoBERTa model, modified in two ways: (1) by injecting additional knowledge (coreferences, named entities, dependency relations, and sentiment) and (2) by leveraging the task uncertainty by using soft labels, Monte Carlo dropout, and threshold optimization. We find that the injection of additional knowledge is not helpful but the uncertainty management mechanisms lead to small but consistent improvements. Our final system based on these findings achieves F1 = 0.575 in the online evaluation, ranking 19th out of 78 systems.- Anthology ID:
- 2022.semeval-1.73
- Volume:
- Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)
- Month:
- July
- Year:
- 2022
- Address:
- Seattle, United States
- Editors:
- Guy Emerson, Natalie Schluter, Gabriel Stanovsky, Ritesh Kumar, Alexis Palmer, Nathan Schneider, Siddharth Singh, Shyam Ratan
- Venue:
- SemEval
- SIG:
- SIGLEX
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 525–532
- Language:
- URL:
- https://aclanthology.org/2022.semeval-1.73
- DOI:
- 10.18653/v1/2022.semeval-1.73
- Cite (ACL):
- Matej Klemen and Marko Robnik-Šikonja. 2022. ULFRI at SemEval-2022 Task 4: Leveraging uncertainty and additional knowledge for patronizing and condescending language detection. In Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), pages 525–532, Seattle, United States. Association for Computational Linguistics.
- Cite (Informal):
- ULFRI at SemEval-2022 Task 4: Leveraging uncertainty and additional knowledge for patronizing and condescending language detection (Klemen & Robnik-Šikonja, SemEval 2022)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2022.semeval-1.73.pdf