← Search

Justin Qiu

2 accepted papers

2025

StyleDistance: Stronger Content-Independent Style Embeddings with Synthetic Parallel Examples

NAACL 2025long

Style representations aim to embed texts with similar writing styles closely and texts with different styles far apart, regardless of content. However, the contrastive triplets often used for training these representations may vary in both style and content, leading to potential content leakage in t…

Cited by 2SourcePDFScholar
2025

mStyleDistance: Multilingual Style Embeddings and their Evaluation

ACL 2025finding

Style embeddings are useful for stylistic analysis and style transfer, yet they only exist for English. We introduce Multilingual StyleDistance (mStyleDistance), a method that can generate style embeddings in new languages using synthetic data and a contrastive loss. We create style embeddings in ni…

Cited by 0SourcePDFScholar