Subcharacter Information in Japanese Embeddings: When Is It Worth It?
Marzena Karpinska, Bofang Li, Anna Rogers, Дрозд Александр Валентинович · 2018
Languages with logographic writing systems present a difficulty for traditional character-level models.Leveraging the subcharacter information was recently shown to be beneficial for a number of intrinsic and extrinsic tasks in Chinese.We examine whether the same strategies could be applied for Japanese, and contribute a new analogy dataset for this language.