Search Results for author: Kento Watanabe

Found 9 papers, 2 papers with code

Self-Supervised Contrastive Learning for Singing Voices

1 code implementation IEEE/ACM Transactions on Audio, Speech, and Language Processing 2022 Hiromu Yakura, Kento Watanabe, Masataka Goto

To acquire robust representations in an unsupervised manner, regular self-supervised contrastive learning trains neural networks to make the feature representation of a sample close to those of its computationally transformed versions.

Contrastive Learning Singer Identification +1

Semi-supervised Learning with Multi-Domain Sentiment Word Embeddings

no code implementations27 Sep 2018 Ran Tian, Yash Agrawal, Kento Watanabe, Hiroya Takamura

Word embeddings are known to boost performance of many NLP tasks such as text classification, meanwhile they can be enhanced by labels at the document level to capture nuanced meaning such as sentiment and topic.

Domain Adaptation text-classification +2

Unsupervised Learning of Style-sensitive Word Vectors

no code implementations ACL 2018 Reina Akama, Kento Watanabe, Sho Yokoi, Sosuke Kobayashi, Kentaro Inui

This paper presents the first study aimed at capturing stylistic similarity between words in an unsupervised manner.

Word Embeddings

Cannot find the paper you are looking for? You can Submit a new open access paper.