@inproceedings{6701d114469c447191a73cd5bdf02f7d,
title = "Syllable-level neural language model for agglutinative language",
abstract = "Language models for agglutinative languages have always been hindered in past due to myriad of agglutinations possible to any given word through various affixes. We propose a method to diminish the problem of out-of-vocabulary words by introducing an embedding derived from syllables and morphemes which leverages the agglutinative property. Our model outperforms character-level embedding in perplexity by 16.87 with 9.50M parameters. Proposed method achieves state of the art performance over existing input prediction methods in terms of Key Stroke Saving and has been commercialized.",
author = "Seunghak Yu and Nilesh Kulkarni and Haejun Lee and Jihie Kim",
note = "Publisher Copyright: {\textcopyright} EMNLP 2017.All right reserved.; EMNLP 2017 1st Workshop on Subword and Character Level Models in NLP, SCLeM 2017 ; Conference date: 07-09-2017",
year = "2017",
language = "English",
series = "EMNLP 2017 - 1st Workshop on Subword and Character Level Models in NLP, SCLeM 2017 - Proceedings of the Workshop",
publisher = "Association for Computational Linguistics (ACL)",
pages = "92--96",
editor = "Manaal Faruqui and Hinrich Schutze and Isabel Trancoso and Yaghoobzadeh Yadollah",
booktitle = "EMNLP 2017 - 1st Workshop on Subword and Character Level Models in NLP, SCLeM 2017 - Proceedings of the Workshop",
address = "United States",
}