Contrastive learning from label distribution: A case study on text classification
2022
over the strong RoBERTa-Large baseline on ten datasets. Particularly, our contrastive learning in the label space can effectively capture label correlations better than that in the embedding space, achieving an improvement of
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
0
References
0
Citations
NaN
KQI