papers AI Learner
The Github is limit! Click to go to the new site.

Segmentation-free Compositional $n$-gram Embedding

2019-05-29
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.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1809.00918

PDF

http://arxiv.org/pdf/1809.00918


Comments

Content