Kanako Komiya

Learning under Covariate Shift for Domain Adaptation for Word Sense Disambiguation

2015 · Institutional Repositories DataBase (IRDB)

We show that domain adaptation for word sense disambiguation (WSD) satisfies the as-sumption of covariate shift, and then solve it by learning under covariate shift. Learning under covariate shift has two key points: (1) calculation …

Unsupervised Domain Adaptation for Word Sense Disambiguation using Stacked Denoising Autoencoder

2015 · Institutional Repositories DataBase (IRDB)

In this paper, we propose an unsupervised do-main adaptation for Word Sense Disambigua-tion (WSD) using Stacked Denoising Autoen-coder (SdA). SdA is an unsupervised learn-ing method of obtaining the abstract feature set of input data using …

Fine-tuning for Named Entity Recognition Using Part-of-Speech Tagging

2018 · Institutional Repositories DataBase (IRDB)

conference paper

Long Unit Word Tokenization and Bunsetsu Segmentation of Historical Japanese

2024

In Japanese, "bunsetsu" is the natural minimal phrase of a sentence; it serves as a natural boundary of a sentence for native speakers rather than words, and thus grammatical analysis in Japanese linguistics commonly operates …