BERTGen: Multi-task Generation through BERT
Faidon Mitzalis, Ozan Caglayan, Pranava Madhyastha, Lucia Specia
Abstract
We present BERTGen, a novel, generative, decoder-only model which extends BERT by fusing multimodal and multilingual pre-trained models VL-BERT and M-BERT, respectively. BERTGen is auto-regressively trained for language generation tasks, namely image captioning, machine translation and multimodal machine translation, under a multi-task setting. With a comprehensive set of evaluations, we show that BERTGen outperforms many strong baselines across the tasks explored. We also show BERTGen’s ability for zero-shot language generation, where it exhibits competitive performance to supervised counterparts. Finally, we conduct ablation studies which demonstrate that BERTGen substantially benefits from multi-tasking and effectively transfers relevant inductive biases from the pre-trained models.- Anthology ID:
- 2021.acl-long.503
- Volume:
- Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
- Month:
- August
- Year:
- 2021
- Address:
- Online
- Editors:
- Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
- Venues:
- ACL | IJCNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 6440–6455
- Language:
- URL:
- https://aclanthology.org/2021.acl-long.503
- DOI:
- 10.18653/v1/2021.acl-long.503
- Cite (ACL):
- Faidon Mitzalis, Ozan Caglayan, Pranava Madhyastha, and Lucia Specia. 2021. BERTGen: Multi-task Generation through BERT. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 6440–6455, Online. Association for Computational Linguistics.
- Cite (Informal):
- BERTGen: Multi-task Generation through BERT (Mitzalis et al., ACL-IJCNLP 2021)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2021.acl-long.503.pdf
- Code
- ImperialNLP/BertGen