← Search

Philip L. H. Yu

2 accepted papers

2022

AutoBERT-Zero: Evolving BERT Backbone from Scratch

AAAI 2022technical

Transformer-based pre-trained language models like BERT and its variants have recently achieved promising performance in various natural language processing (NLP) tasks. However, the conventional paradigm constructs the backbone by purely stacking the manually designed global self-attention layers,…

Cited by 44SourcePDFScholar
2022

UNISON: Unpaired Cross-Lingual Image Captioning

AAAI 2022technical

Image captioning has emerged as an interesting research field in recent years due to its broad application scenarios. The traditional paradigm of image captioning relies on paired image-caption datasets to train the model in a supervised manner. However, creating such paired datasets for every targe…