Reusing Weights in Subword-Aware Neural Language Models

Zhenisbek Assylbekov, Rustem Takhanov


Abstract
We propose several ways of reusing subword embeddings and other weights in subword-aware neural language models. The proposed techniques do not benefit a competitive character-aware model, but some of them improve the performance of syllable- and morpheme-aware models while showing significant reductions in model sizes. We discover a simple hands-on principle: in a multi-layer input embedding model, layers should be tied consecutively bottom-up if reused at output. Our best morpheme-aware model with properly reused weights beats the competitive word-level model by a large margin across multiple languages and has 20%-87% fewer parameters.
Anthology ID:
N18-1128
Volume:
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)
Month:
June
Year:
2018
Address:
New Orleans, Louisiana
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1413–1423
Language:
URL:
https://www.aclweb.org/anthology/N18-1128
DOI:
10.18653/v1/N18-1128
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/N18-1128.pdf