@inproceedings{wu-etal-2019-learning,
title = "Learning to Learn and Predict: A Meta-Learning Approach for Multi-Label Classification",
author = "Wu, Jiawei and
Xiong, Wenhan and
Wang, William Yang",
editor = "Inui, Kentaro and
Jiang, Jing and
Ng, Vincent and
Wan, Xiaojun",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-1444",
doi = "10.18653/v1/D19-1444",
pages = "4354--4364",
abstract = "Many tasks in natural language processing can be viewed as multi-label classification problems. However, most of the existing models are trained with the standard cross-entropy loss function and use a fixed prediction policy (e.g., a threshold of 0.5) for all the labels, which completely ignores the complexity and dependencies among different labels. In this paper, we propose a meta-learning method to capture these complex label dependencies. More specifically, our method utilizes a meta-learner to jointly learn the training policies and prediction policies for different labels. The training policies are then used to train the classifier with the cross-entropy loss function, and the prediction policies are further implemented for prediction. Experimental results on fine-grained entity typing and text classification demonstrate that our proposed method can obtain more accurate multi-label classification results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2019-learning">
<titleInfo>
<title>Learning to Learn and Predict: A Meta-Learning Approach for Multi-Label Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiawei</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenhan</namePart>
<namePart type="family">Xiong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="given">Yang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Many tasks in natural language processing can be viewed as multi-label classification problems. However, most of the existing models are trained with the standard cross-entropy loss function and use a fixed prediction policy (e.g., a threshold of 0.5) for all the labels, which completely ignores the complexity and dependencies among different labels. In this paper, we propose a meta-learning method to capture these complex label dependencies. More specifically, our method utilizes a meta-learner to jointly learn the training policies and prediction policies for different labels. The training policies are then used to train the classifier with the cross-entropy loss function, and the prediction policies are further implemented for prediction. Experimental results on fine-grained entity typing and text classification demonstrate that our proposed method can obtain more accurate multi-label classification results.</abstract>
<identifier type="citekey">wu-etal-2019-learning</identifier>
<identifier type="doi">10.18653/v1/D19-1444</identifier>
<location>
<url>https://aclanthology.org/D19-1444</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>4354</start>
<end>4364</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning to Learn and Predict: A Meta-Learning Approach for Multi-Label Classification
%A Wu, Jiawei
%A Xiong, Wenhan
%A Wang, William Yang
%Y Inui, Kentaro
%Y Jiang, Jing
%Y Ng, Vincent
%Y Wan, Xiaojun
%S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F wu-etal-2019-learning
%X Many tasks in natural language processing can be viewed as multi-label classification problems. However, most of the existing models are trained with the standard cross-entropy loss function and use a fixed prediction policy (e.g., a threshold of 0.5) for all the labels, which completely ignores the complexity and dependencies among different labels. In this paper, we propose a meta-learning method to capture these complex label dependencies. More specifically, our method utilizes a meta-learner to jointly learn the training policies and prediction policies for different labels. The training policies are then used to train the classifier with the cross-entropy loss function, and the prediction policies are further implemented for prediction. Experimental results on fine-grained entity typing and text classification demonstrate that our proposed method can obtain more accurate multi-label classification results.
%R 10.18653/v1/D19-1444
%U https://aclanthology.org/D19-1444
%U https://doi.org/10.18653/v1/D19-1444
%P 4354-4364
Markdown (Informal)
[Learning to Learn and Predict: A Meta-Learning Approach for Multi-Label Classification](https://aclanthology.org/D19-1444) (Wu et al., EMNLP-IJCNLP 2019)
ACL