Abstract
This paper presents our submission to Task 2 of the Workshop on Noisy User-generated Text. We explore improving the performance of a pre-trained transformer-based language model fine-tuned for text classification through an ensemble implementation that makes use of corpus level information and a handcrafted feature. We test the effectiveness of including the aforementioned features in accommodating the challenges of a noisy data set centred on a specific subject outside the remit of the pre-training data. We show that inclusion of additional features can improve classification results and achieve a score within 2 points of the top performing team.- Anthology ID:
- 2020.wnut-1.48
- Volume:
- Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020)
- Month:
- November
- Year:
- 2020
- Address:
- Online
- Venue:
- WNUT
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 352–358
- Language:
- URL:
- https://aclanthology.org/2020.wnut-1.48
- DOI:
- 10.18653/v1/2020.wnut-1.48
- Cite (ACL):
- Calum Perrio and Harish Tayyar Madabushi. 2020. CXP949 at WNUT-2020 Task 2: Extracting Informative COVID-19 Tweets - RoBERTa Ensembles and The Continued Relevance of Handcrafted Features. In Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020), pages 352–358, Online. Association for Computational Linguistics.
- Cite (Informal):
- CXP949 at WNUT-2020 Task 2: Extracting Informative COVID-19 Tweets - RoBERTa Ensembles and The Continued Relevance of Handcrafted Features (Perrio & Tayyar Madabushi, WNUT 2020)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/2020.wnut-1.48.pdf