2000 character limit reached
Marvelous Agglutinative Language Effect on Cross Lingual Transfer Learning (2204.03831v3)
Published 8 Apr 2022 in cs.CL
Abstract: As for multilingual LLMs, it is important to select languages for training because of the curse of multilinguality. It is known that using languages with similar language structures is effective for cross lingual transfer learning. However, we demonstrate that using agglutinative languages such as Korean is more effective in cross lingual transfer learning. This is a great discovery that will change the training strategy of cross lingual transfer learning.
Collections
Sign up for free to add this paper to one or more collections.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.