Subcharacter Information in Japanese Embeddings: When Is It Worth It?

Marzena Karpinska; Bofang Li; Anna Rogers; Aleksandr Drozd

Subcharacter Information in Japanese Embeddings: When Is It Worth It?

Marzena Karpinska, Bofang Li, Anna Rogers, Aleksandr Drozd

Research output: Conference Article in Proceeding or Book/Report chapter › Article in proceedings › Research › peer-review

Abstract

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.

Original language	English
Title of host publication	Proceedings of the Workshop on the Relevance of Linguistic Structure in Neural Architectures for NLP
Number of pages	10
Place of Publication	Melbourne, Australia
Publisher	Association for Computational Linguistics
Publication date	2018
Pages	28-37
Publication status	Published - 2018

Keywords

Logographic writing systems
Character-level models
Subcharacter information
Chinese language processing
Japanese language analogies

Access to Document

http://aclweb.org/anthology/W18-2905

Cite this

@inproceedings{c016d87e18954d50a2ff9695b3a5536e,

title = "Subcharacter Information in Japanese Embeddings: When Is It Worth It?",

abstract = "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.",

keywords = "Logographic writing systems, Character-level models, Subcharacter information, Chinese language processing, Japanese language analogies",

author = "Marzena Karpinska and Bofang Li and Anna Rogers and Aleksandr Drozd",

year = "2018",

language = "English",

pages = "28--37",

booktitle = "Proceedings of the Workshop on the Relevance of Linguistic Structure in Neural Architectures for NLP",

publisher = "Association for Computational Linguistics",

address = "United States",

}

Subcharacter Information in Japanese Embeddings: When Is It Worth It? / Karpinska, Marzena; Li, Bofang; Rogers, Anna et al.
Proceedings of the Workshop on the Relevance of Linguistic Structure in Neural Architectures for NLP. Melbourne, Australia: Association for Computational Linguistics, 2018. p. 28-37.

Research output: Conference Article in Proceeding or Book/Report chapter › Article in proceedings › Research › peer-review