Abstract
In this report, we describe our transformers for text classification baseline (TTCB) submissions to a shared task on implicit and underspecified language 2021. We cast the task of predicting revision requirements in collaboratively edited instructions as text classification. We considered transformer-based models which are the current state-of-the-art methods for text classification. We explored different training schemes, loss functions, and data augmentations. Our best result of 68.45% test accuracy (68.84% validation accuracy), however, consists of an XLNet model with a linear annealing scheduler and a cross-entropy loss. We do not observe any significant gain on any validation metric based on our various design choices except the MiniLM which has a higher validation F1 score and is faster to train by a half but also a lower validation accuracy score.- Anthology ID:
- 2021.unimplicit-1.8
- Volume:
- Proceedings of the 1st Workshop on Understanding Implicit and Underspecified Language
- Month:
- August
- Year:
- 2021
- Address:
- Online
- Editors:
- Michael Roth, Reut Tsarfaty, Yoav Goldberg
- Venue:
- unimplicit
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 64–70
- Language:
- URL:
- https://aclanthology.org/2021.unimplicit-1.8
- DOI:
- 10.18653/v1/2021.unimplicit-1.8
- Cite (ACL):
- Peratham Wiriyathammabhum. 2021. TTCB System Description to a Shared Task on Implicit and Underspecified Language 2021. In Proceedings of the 1st Workshop on Understanding Implicit and Underspecified Language, pages 64–70, Online. Association for Computational Linguistics.
- Cite (Informal):
- TTCB System Description to a Shared Task on Implicit and Underspecified Language 2021 (Wiriyathammabhum, unimplicit 2021)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2021.unimplicit-1.8.pdf