CLIP Also Understands Text: Prompting CLIP For Phrase Understanding

Yan An, Li Jiacheng, Zhu Wanrong, Lu Yujie, Wang William Yang, Mcauley Julian. Arxiv 2022

[Paper]    
BERT Fine Tuning Model Architecture Pretraining Methods Prompting Reinforcement Learning Training Techniques

Contrastive Language-Image Pretraining (CLIP) efficiently learns visual concepts by pre-training with natural language supervision. CLIP and its visual encoder have been explored on various vision and language tasks and achieve strong zero-shot or transfer learning performance. However, the application of its text encoder solely for text understanding has been less explored. In this paper, we find that the text encoder of CLIP actually demonstrates strong ability for phrase understanding, and can even significantly outperform popular language models such as BERT with a properly designed prompt. Extensive experiments validate the effectiveness of our method across different datasets and domains on entity clustering and entity set expansion tasks.

Similar Work