Faidon Mitzalis


2021

pdf bib
BERTGen: Multi-task Generation through BERT
Faidon Mitzalis | Ozan Caglayan | Pranava Madhyastha | Lucia Specia
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)

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.