Syllable-aware Neural Language Models: A Failure to Beat Character-aware Ones
arXiv:1707.06480v11089 citations
Originality Synthesis-oriented
AI Analysis
This addresses the efficiency of language models for NLP researchers, but is incremental as it shows no quality improvement over existing methods.
The paper tackled the problem of improving neural language models by using syllable-aware segmentation, but found it did not beat character-aware models in quality, though it achieved comparable performance with 18%-33% fewer parameters and 1.2-2.2 times faster training.
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.