IDIOLEX learns unified continuous representations of idiolectal and stylistic variation decoupled from semantics by combining provenance supervision with linguistic features, evaluated on Arabic and Spanish dialects with transfer and LM alignment uses.
Same Author or Just Same Topic? Towards Content-Independent Style Representations , shorttitle =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2representative citing papers
citing papers explorer
-
IDIOLEX: Unified and Continuous Representations for Idiolectal and Stylistic Variation
IDIOLEX learns unified continuous representations of idiolectal and stylistic variation decoupled from semantics by combining provenance supervision with linguistic features, evaluated on Arabic and Spanish dialects with transfer and LM alignment uses.
- Where Does Authorship Signal Emerge in Encoder-Based Language Models?