Segmentation-free compositional n-gram embedding

Geewook Kim, Kazuki Fukui, Hidetoshi Shimodaira


Abstract
We propose a new type of representation learning method that models words, phrases and sentences seamlessly. Our method does not depend on word segmentation and any human-annotated resources (e.g., word dictionaries), yet it is very effective for noisy corpora written in unsegmented languages such as Chinese and Japanese. The main idea of our method is to ignore word boundaries completely (i.e., segmentation-free), and construct representations for all character n-grams in a raw corpus with embeddings of compositional sub-n-grams. Although the idea is simple, our experiments on various benchmarks and real-world datasets show the efficacy of our proposal.
Anthology ID:
N19-1324
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3207–3215
Language:
URL:
https://www.aclweb.org/anthology/N19-1324
DOI:
10.18653/v1/N19-1324
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/N19-1324.pdf
Supplementary:
 N19-1324.Supplementary.pdf