@inproceedings{banerjee-etal-2019-hierarchical,
title = "Hierarchical Transfer Learning for Multi-label Text Classification",
author = "Banerjee, Siddhartha and
Akkaya, Cem and
Perez-Sorrosal, Francisco and
Tsioutsiouliklis, Kostas",
editor = "Korhonen, Anna and
Traum, David and
M{\`a}rquez, Llu{\'\i}s",
booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P19-1633",
doi = "10.18653/v1/P19-1633",
pages = "6295--6300",
abstract = "Multi-Label Hierarchical Text Classification (MLHTC) is the task of categorizing documents into one or more topics organized in an hierarchical taxonomy. MLHTC can be formulated by combining multiple binary classification problems with an independent classifier for each category. We propose a novel transfer learning based strategy, HTrans, where binary classifiers at lower levels in the hierarchy are initialized using parameters of the parent classifier and fine-tuned on the child category classification task. In HTrans, we use a Gated Recurrent Unit (GRU)-based deep learning architecture coupled with attention. Compared to binary classifiers trained from scratch, our HTrans approach results in significant improvements of 1{\%} on micro-F1 and 3{\%} on macro-F1 on the RCV1 dataset. Our experiments also show that binary classifiers trained from scratch are significantly better than single multi-label models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="banerjee-etal-2019-hierarchical">
<titleInfo>
<title>Hierarchical Transfer Learning for Multi-label Text Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Siddhartha</namePart>
<namePart type="family">Banerjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cem</namePart>
<namePart type="family">Akkaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francisco</namePart>
<namePart type="family">Perez-Sorrosal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kostas</namePart>
<namePart type="family">Tsioutsiouliklis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</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">David</namePart>
<namePart type="family">Traum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Màrquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multi-Label Hierarchical Text Classification (MLHTC) is the task of categorizing documents into one or more topics organized in an hierarchical taxonomy. MLHTC can be formulated by combining multiple binary classification problems with an independent classifier for each category. We propose a novel transfer learning based strategy, HTrans, where binary classifiers at lower levels in the hierarchy are initialized using parameters of the parent classifier and fine-tuned on the child category classification task. In HTrans, we use a Gated Recurrent Unit (GRU)-based deep learning architecture coupled with attention. Compared to binary classifiers trained from scratch, our HTrans approach results in significant improvements of 1% on micro-F1 and 3% on macro-F1 on the RCV1 dataset. Our experiments also show that binary classifiers trained from scratch are significantly better than single multi-label models.</abstract>
<identifier type="citekey">banerjee-etal-2019-hierarchical</identifier>
<identifier type="doi">10.18653/v1/P19-1633</identifier>
<location>
<url>https://aclanthology.org/P19-1633</url>
</location>
<part>
<date>2019-07</date>
<extent unit="page">
<start>6295</start>
<end>6300</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Hierarchical Transfer Learning for Multi-label Text Classification
%A Banerjee, Siddhartha
%A Akkaya, Cem
%A Perez-Sorrosal, Francisco
%A Tsioutsiouliklis, Kostas
%Y Korhonen, Anna
%Y Traum, David
%Y Màrquez, Lluís
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019
%8 July
%I Association for Computational Linguistics
%C Florence, Italy
%F banerjee-etal-2019-hierarchical
%X Multi-Label Hierarchical Text Classification (MLHTC) is the task of categorizing documents into one or more topics organized in an hierarchical taxonomy. MLHTC can be formulated by combining multiple binary classification problems with an independent classifier for each category. We propose a novel transfer learning based strategy, HTrans, where binary classifiers at lower levels in the hierarchy are initialized using parameters of the parent classifier and fine-tuned on the child category classification task. In HTrans, we use a Gated Recurrent Unit (GRU)-based deep learning architecture coupled with attention. Compared to binary classifiers trained from scratch, our HTrans approach results in significant improvements of 1% on micro-F1 and 3% on macro-F1 on the RCV1 dataset. Our experiments also show that binary classifiers trained from scratch are significantly better than single multi-label models.
%R 10.18653/v1/P19-1633
%U https://aclanthology.org/P19-1633
%U https://doi.org/10.18653/v1/P19-1633
%P 6295-6300
Markdown (Informal)
[Hierarchical Transfer Learning for Multi-label Text Classification](https://aclanthology.org/P19-1633) (Banerjee et al., ACL 2019)
ACL
- Siddhartha Banerjee, Cem Akkaya, Francisco Perez-Sorrosal, and Kostas Tsioutsiouliklis. 2019. Hierarchical Transfer Learning for Multi-label Text Classification. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 6295–6300, Florence, Italy. Association for Computational Linguistics.