Computationally efficient wasserstein loss for structured labels

Ayato Toyokuni, Sho Yokoi, Hisashi Kashima, Makoto Yamada

研究成果: Conference contribution

抄録

The problem of estimating the probability distribution of labels has been widely studied as a label distribution learning (LDL) problem, whose applications include age estimation, emotion analysis, and semantic segmentation. We propose a tree-Wasserstein distance regularized LDL algorithm, focusing on hierarchical text classification tasks. We propose predicting the entire label hierarchy using neural networks, where the similarity between predicted and true labels is measured using the tree-Wasserstein distance. Through experiments using synthetic and real-world datasets, we demonstrate that the proposed method successfully considers the structure of labels during training, and it compares favorably with the Sinkhorn algorithm in terms of computation time and memory usage.

本文言語English
ホスト出版物のタイトルEACL 2021 - 16th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Student Research Workshop
出版社Association for Computational Linguistics (ACL)
ページ1-7
ページ数7
ISBN(電子版)9781954085046
出版ステータスPublished - 2021
イベント16th Conference of the European Chapter of the Associationfor Computational Linguistics: Student Research Workshop, EACL 2021 - Virtual, Online
継続期間: 2021 4 192021 4 23

出版物シリーズ

名前EACL 2021 - 16th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Student Research Workshop

Conference

Conference16th Conference of the European Chapter of the Associationfor Computational Linguistics: Student Research Workshop, EACL 2021
CityVirtual, Online
Period21/4/1921/4/23

ASJC Scopus subject areas

  • ソフトウェア
  • 計算理論と計算数学
  • 言語学および言語

フィンガープリント

「Computationally efficient wasserstein loss for structured labels」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル