SEBGM: Sentence Embedding Based on Generation Model with multi-task learning

Qian Wang, Weiqi Zhang, Tianyi Lei, Yu Cao, Dezhong Peng, Xu Wang

Abstract: Highlights•We design a contrastive framework based on generation model with multi-task learning.•We propose a continuous prompt template to help model digest sentence embedding task.•State-of-the-art results are achieved on the semantic textual similarity tasks.