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

Zhenisbek Assylbekov, Rustem Takhanov, Bagdat Myrzakhmetov, Jonathan N. Washington


Abstract
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.
Anthology ID:
D17-1199
Volume:
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Editors:
Martha Palmer, Rebecca Hwa, Sebastian Riedel
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1866–1872
Language:
URL:
https://aclanthology.org/D17-1199
DOI:
10.18653/v1/D17-1199
Bibkey:
Cite (ACL):
Zhenisbek Assylbekov, Rustem Takhanov, Bagdat Myrzakhmetov, and Jonathan N. Washington. 2017. Syllable-aware Neural Language Models: A Failure to Beat Character-aware Ones. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 1866–1872, Copenhagen, Denmark. Association for Computational Linguistics.
Cite (Informal):
Syllable-aware Neural Language Models: A Failure to Beat Character-aware Ones (Assylbekov et al., EMNLP 2017)
Copy Citation:
PDF:
https://aclanthology.org/D17-1199.pdf
Code
 zh3nis/lstm-syl