Mixup-Transformer: Dynamic Data Augmentation for NLP Tasks
Lichao Sun, Congying Xia, Wenpeng Yin, Tingting Liang, Philip Yu, Lifang He
Abstract
Mixup is a latest data augmentation technique that linearly interpolates input examples and the corresponding labels. It has shown strong effectiveness in image classification by interpolating images at the pixel level. Inspired by this line of research, in this paper, we explore i) how to apply mixup to natural language processing tasks since text data can hardly be mixed in the raw format; ii) if mixup is still effective in transformer-based learning models,e.g., BERT.To achieve the goal, we incorporate mixup to transformer-based pre-trained architecture, named“mixup-transformer”, for a wide range of NLP tasks while keeping the whole end-to-end training system. We evaluate the proposed framework by running extensive experiments on the GLUEbenchmark. Furthermore, we also examine the performance of mixup-transformer in low-resource scenarios by reducing the training data with a certain ratio. Our studies show that mixup is a domain-independent data augmentation technique to pre-trained language models, resulting in significant performance improvement for transformer-based models.- Anthology ID:
- 2020.coling-main.305
- Volume:
- Proceedings of the 28th International Conference on Computational Linguistics
- Month:
- December
- Year:
- 2020
- Address:
- Barcelona, Spain (Online)
- Editors:
- Donia Scott, Nuria Bel, Chengqing Zong
- Venue:
- COLING
- SIG:
- Publisher:
- International Committee on Computational Linguistics
- Note:
- Pages:
- 3436–3440
- Language:
- URL:
- https://aclanthology.org/2020.coling-main.305
- DOI:
- 10.18653/v1/2020.coling-main.305
- Cite (ACL):
- Lichao Sun, Congying Xia, Wenpeng Yin, Tingting Liang, Philip Yu, and Lifang He. 2020. Mixup-Transformer: Dynamic Data Augmentation for NLP Tasks. In Proceedings of the 28th International Conference on Computational Linguistics, pages 3436–3440, Barcelona, Spain (Online). International Committee on Computational Linguistics.
- Cite (Informal):
- Mixup-Transformer: Dynamic Data Augmentation for NLP Tasks (Sun et al., COLING 2020)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2020.coling-main.305.pdf
- Data
- CoLA, GLUE, MRPC, MultiNLI, QNLI, SST, SST-2