@inproceedings{toyokuni-etal-2021-computationally,
title = "Computationally Efficient {W}asserstein Loss for Structured Labels",
author = "Toyokuni, Ayato and
Yokoi, Sho and
Kashima, Hisashi and
Yamada, Makoto",
editor = "Sorodoc, Ionut-Teodor and
Sushil, Madhumita and
Takmaz, Ece and
Agirre, Eneko",
booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.eacl-srw.1",
doi = "10.18653/v1/2021.eacl-srw.1",
pages = "1--7",
abstract = "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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="toyokuni-etal-2021-computationally">
<titleInfo>
<title>Computationally Efficient Wasserstein Loss for Structured Labels</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ayato</namePart>
<namePart type="family">Toyokuni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sho</namePart>
<namePart type="family">Yokoi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hisashi</namePart>
<namePart type="family">Kashima</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Makoto</namePart>
<namePart type="family">Yamada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ionut-Teodor</namePart>
<namePart type="family">Sorodoc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Madhumita</namePart>
<namePart type="family">Sushil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ece</namePart>
<namePart type="family">Takmaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eneko</namePart>
<namePart type="family">Agirre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>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.</abstract>
<identifier type="citekey">toyokuni-etal-2021-computationally</identifier>
<identifier type="doi">10.18653/v1/2021.eacl-srw.1</identifier>
<location>
<url>https://aclanthology.org/2021.eacl-srw.1</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>1</start>
<end>7</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Computationally Efficient Wasserstein Loss for Structured Labels
%A Toyokuni, Ayato
%A Yokoi, Sho
%A Kashima, Hisashi
%A Yamada, Makoto
%Y Sorodoc, Ionut-Teodor
%Y Sushil, Madhumita
%Y Takmaz, Ece
%Y Agirre, Eneko
%S Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F toyokuni-etal-2021-computationally
%X 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.
%R 10.18653/v1/2021.eacl-srw.1
%U https://aclanthology.org/2021.eacl-srw.1
%U https://doi.org/10.18653/v1/2021.eacl-srw.1
%P 1-7
Markdown (Informal)
[Computationally Efficient Wasserstein Loss for Structured Labels](https://aclanthology.org/2021.eacl-srw.1) (Toyokuni et al., EACL 2021)
ACL
- Ayato Toyokuni, Sho Yokoi, Hisashi Kashima, and Makoto Yamada. 2021. Computationally Efficient Wasserstein Loss for Structured Labels. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop, pages 1–7, Online. Association for Computational Linguistics.