Syllable-aware Neural Language Models: A Failure to Beat Character-aware Ones

Autor:	Assylbekov, Zhenisbek, Takhanov, Rustem, Myrzakhmetov, Bagdat, Washington, Jonathan N.
Rok vydání:	2017
Předmět:	Computer Science - Computation and Language Computer Science - Neural and Evolutionary Computing Statistics - Machine Learning 68T50 I.2.7
Druh dokumentu:	Working Paper
Popis:	Syllabification does not seem to improve word-level RNN language modeling quality when compared to character-based segmentation. However, our best syllable-aware language model, achieving performance comparable to the competitive character-aware model, has 18%-33% fewer parameters and is trained 1.2-2.2 times faster. Comment: EMNLP 2017
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1707.06480 Zobrazit plný text záznamu View this record from Arxiv