Syllable-level Neural Language Model for Agglutinative Language

Autor:	Yu, Seunghak, Kulkarni, Nilesh, Lee, Haejun, Kim, Jihie
Rok vydání:	2017
Předmět:	Computer Science - Computation and Language
Druh dokumentu:	Working Paper
Popis:	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. Comment: Accepted at EMNLP 2017 workshop on Subword and Character level models in NLP (SCLeM)
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1708.05515 Zobrazit plný text záznamu View this record from Arxiv