Segmentation-free Compositional $n$-gram Embedding
This addresses the challenge of noisy corpora in languages without clear word boundaries, offering a resource-light approach.
The paper tackles the problem of representation learning for unsegmented languages like Chinese and Japanese by proposing a segmentation-free method that models words, phrases, and sentences using character n-gram embeddings, achieving effectiveness on benchmarks and real-world datasets.
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.