April 22, 2024, 4:42 a.m. | Hoang H. Nguyen, Chenwei Zhang, Ye Liu, Natalie Parde, Eugene Rohrbaugh, Philip S. Yu

cs.LG updates on arXiv.org arxiv.org

arXiv:2404.12618v1 Announce Type: cross
Abstract: Naively assuming English as a source language may hinder cross-lingual transfer for many languages by failing to consider the importance of language contact. Some languages are more well-connected than others, and target languages can benefit from transferring from closely related languages; for many languages, the set of closely related languages does not include English. In this work, we study the impact of source language for cross-lingual transfer, demonstrating the importance of selecting source languages that …

abstract arxiv benchmark benefit beyond cross-lingual cs.ai cs.cl cs.lg english hinder importance integration language languages scripts textual transfer type

Lead Developer (AI)

@ Cere Network | San Francisco, US

Research Engineer

@ Allora Labs | Remote

Ecosystem Manager

@ Allora Labs | Remote

Founding AI Engineer, Agents

@ Occam AI | New York

AI Engineer Intern, Agents

@ Occam AI | US

AI Research Scientist

@ Vara | Berlin, Germany and Remote