@inproceedings{yoshikawa-iwakura-2018-model,
title = "Model Transfer with Explicit Knowledge of the Relation between Class Definitions",
author = "Yoshikawa, Hiyori and
Iwakura, Tomoya",
editor = "Korhonen, Anna and
Titov, Ivan",
booktitle = "Proceedings of the 22nd Conference on Computational Natural Language Learning",
month = oct,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/K18-1052",
doi = "10.18653/v1/K18-1052",
pages = "541--550",
abstract = "This paper investigates learning methods for multi-class classification using labeled data for the target classification scheme and another labeled data for a similar but different classification scheme (support scheme). We show that if we have prior knowledge about the relation between support and target classification schemes in the form of a class correspondence table, we can use it to improve the model performance further than the simple multi-task learning approach. Instead of learning the individual classification layers for the support and target schemes, the proposed method converts the class label of each example on the support scheme into a set of candidate class labels on the target scheme via the class correspondence table, and then uses the candidate labels to learn the classification layer for the target scheme. We evaluate the proposed method on two tasks in NLP. The experimental results show that our method effectively learns the target schemes especially for the classes that have a tight connection to certain support classes.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yoshikawa-iwakura-2018-model">
<titleInfo>
<title>Model Transfer with Explicit Knowledge of the Relation between Class Definitions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hiyori</namePart>
<namePart type="family">Yoshikawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomoya</namePart>
<namePart type="family">Iwakura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 22nd Conference on Computational Natural Language Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Korhonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Titov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Brussels, Belgium</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper investigates learning methods for multi-class classification using labeled data for the target classification scheme and another labeled data for a similar but different classification scheme (support scheme). We show that if we have prior knowledge about the relation between support and target classification schemes in the form of a class correspondence table, we can use it to improve the model performance further than the simple multi-task learning approach. Instead of learning the individual classification layers for the support and target schemes, the proposed method converts the class label of each example on the support scheme into a set of candidate class labels on the target scheme via the class correspondence table, and then uses the candidate labels to learn the classification layer for the target scheme. We evaluate the proposed method on two tasks in NLP. The experimental results show that our method effectively learns the target schemes especially for the classes that have a tight connection to certain support classes.</abstract>
<identifier type="citekey">yoshikawa-iwakura-2018-model</identifier>
<identifier type="doi">10.18653/v1/K18-1052</identifier>
<location>
<url>https://aclanthology.org/K18-1052</url>
</location>
<part>
<date>2018-10</date>
<extent unit="page">
<start>541</start>
<end>550</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Model Transfer with Explicit Knowledge of the Relation between Class Definitions
%A Yoshikawa, Hiyori
%A Iwakura, Tomoya
%Y Korhonen, Anna
%Y Titov, Ivan
%S Proceedings of the 22nd Conference on Computational Natural Language Learning
%D 2018
%8 October
%I Association for Computational Linguistics
%C Brussels, Belgium
%F yoshikawa-iwakura-2018-model
%X This paper investigates learning methods for multi-class classification using labeled data for the target classification scheme and another labeled data for a similar but different classification scheme (support scheme). We show that if we have prior knowledge about the relation between support and target classification schemes in the form of a class correspondence table, we can use it to improve the model performance further than the simple multi-task learning approach. Instead of learning the individual classification layers for the support and target schemes, the proposed method converts the class label of each example on the support scheme into a set of candidate class labels on the target scheme via the class correspondence table, and then uses the candidate labels to learn the classification layer for the target scheme. We evaluate the proposed method on two tasks in NLP. The experimental results show that our method effectively learns the target schemes especially for the classes that have a tight connection to certain support classes.
%R 10.18653/v1/K18-1052
%U https://aclanthology.org/K18-1052
%U https://doi.org/10.18653/v1/K18-1052
%P 541-550
Markdown (Informal)
[Model Transfer with Explicit Knowledge of the Relation between Class Definitions](https://aclanthology.org/K18-1052) (Yoshikawa & Iwakura, CoNLL 2018)
ACL