@inproceedings{zhou-etal-2025-novel,
title = "A Novel Negative Sample Generation Method for Contrastive Learning in Hierarchical Text Classification",
author = "Zhou, Juncheng and
Zhang, Lijuan and
He, Yachen and
Fan, Rongli and
Zhang, Lei and
Wan, Jian",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.378/",
pages = "5645--5655",
abstract = "Hierarchical text classification (HTC) is an important task in natural language processing (NLP). Existing methods typically utilize both text features and the hierarchical structure of labels to categorize text effectively. However, these approaches often struggle with fine-grained labels, which are closely similar, leading to difficulties in accurate classification. At the same time, contrastive learning has significant advantages in strengthening fine-grained label features and discrimination. However, the performance of contrastive learning strongly depends on the construction of negative samples. In this paper, we design a hierarchical sequence ranking (HiSR) method for generating diverse negative samples. These samples maximize the effectiveness of contrastive learning to enhance the ability of the model to distinguish between fine-grained labels and improve the performance of the model in HTC. Specifically, we transform the entire label set into linear sequences based on the hierarchical structure and rank these sequences according to their quality. During model training, the most suitable negative samples were dynamically selected from the ranked sequences. Then contrastive learning amplifies the differences between similar fine-grained labels by emphasizing the distinction between the ground truth and the generated negative samples, thereby enhancing the discriminative ability of the model. Our method has been tested on three public datasets and achieves state-of-art (SOTA) on two of them, demonstrating its effectiveness."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhou-etal-2025-novel">
<titleInfo>
<title>A Novel Negative Sample Generation Method for Contrastive Learning in Hierarchical Text Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Juncheng</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lijuan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yachen</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rongli</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jian</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Hierarchical text classification (HTC) is an important task in natural language processing (NLP). Existing methods typically utilize both text features and the hierarchical structure of labels to categorize text effectively. However, these approaches often struggle with fine-grained labels, which are closely similar, leading to difficulties in accurate classification. At the same time, contrastive learning has significant advantages in strengthening fine-grained label features and discrimination. However, the performance of contrastive learning strongly depends on the construction of negative samples. In this paper, we design a hierarchical sequence ranking (HiSR) method for generating diverse negative samples. These samples maximize the effectiveness of contrastive learning to enhance the ability of the model to distinguish between fine-grained labels and improve the performance of the model in HTC. Specifically, we transform the entire label set into linear sequences based on the hierarchical structure and rank these sequences according to their quality. During model training, the most suitable negative samples were dynamically selected from the ranked sequences. Then contrastive learning amplifies the differences between similar fine-grained labels by emphasizing the distinction between the ground truth and the generated negative samples, thereby enhancing the discriminative ability of the model. Our method has been tested on three public datasets and achieves state-of-art (SOTA) on two of them, demonstrating its effectiveness.</abstract>
<identifier type="citekey">zhou-etal-2025-novel</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.378/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>5645</start>
<end>5655</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Novel Negative Sample Generation Method for Contrastive Learning in Hierarchical Text Classification
%A Zhou, Juncheng
%A Zhang, Lijuan
%A He, Yachen
%A Fan, Rongli
%A Zhang, Lei
%A Wan, Jian
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F zhou-etal-2025-novel
%X Hierarchical text classification (HTC) is an important task in natural language processing (NLP). Existing methods typically utilize both text features and the hierarchical structure of labels to categorize text effectively. However, these approaches often struggle with fine-grained labels, which are closely similar, leading to difficulties in accurate classification. At the same time, contrastive learning has significant advantages in strengthening fine-grained label features and discrimination. However, the performance of contrastive learning strongly depends on the construction of negative samples. In this paper, we design a hierarchical sequence ranking (HiSR) method for generating diverse negative samples. These samples maximize the effectiveness of contrastive learning to enhance the ability of the model to distinguish between fine-grained labels and improve the performance of the model in HTC. Specifically, we transform the entire label set into linear sequences based on the hierarchical structure and rank these sequences according to their quality. During model training, the most suitable negative samples were dynamically selected from the ranked sequences. Then contrastive learning amplifies the differences between similar fine-grained labels by emphasizing the distinction between the ground truth and the generated negative samples, thereby enhancing the discriminative ability of the model. Our method has been tested on three public datasets and achieves state-of-art (SOTA) on two of them, demonstrating its effectiveness.
%U https://aclanthology.org/2025.coling-main.378/
%P 5645-5655
Markdown (Informal)
[A Novel Negative Sample Generation Method for Contrastive Learning in Hierarchical Text Classification](https://aclanthology.org/2025.coling-main.378/) (Zhou et al., COLING 2025)
ACL