Roshane Shahbaz

One Language, Two Unequal Scripts: Separating Orthography from Information in Multilingual Representations with Punjabi

Multilingual models are said to abstract away script in their middle layers. Tests usually compare languages that differ in script and language at once. Punjabi does not. It is written in Gurmukhi and in Shahmukhi, which differ in what they record, since unvocalised Shahmukhi lea...