BlendCSE: blend contrastive learnings for sentence embeddings with rich semantics and transferability
Sentence representation is one of the most fundamental research topics in natural language processing (NLP), as its quality directly affects various downstream task performances. Recent studies for sentence representations have established state-of-the-art (SOTA) performance on semantic representati...
Saved in:
Main Authors: | Xu, Jiahao, Soh, Charlie Zhanyi, Xu, Liwen, Chen, Lihui |
---|---|
其他作者: | School of Electrical and Electronic Engineering |
格式: | Article |
語言: | English |
出版: |
2024
|
主題: | |
在線閱讀: | https://hdl.handle.net/10356/173052 |
標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
相似書籍
-
Composition distillation for semantic sentence embeddings
由: Vaanavan, Sezhiyan
出版: (2024) -
Large language model enhanced with prompt-based vanilla distillation for sentence embeddings
由: Wang, Minghao
出版: (2024) -
Mutual-reinforcement document summarization using embedded graph based sentence clustering for storytelling
由: Zhang, Z., et al.
出版: (2014) -
When missing NPs make double center-embedding sentences acceptable
由: Huang, Nick, et al.
出版: (2022) -
On-the-fly knowledge distillation model for sentence embedding
由: Zhu, Xuchun
出版: (2024)