Incorporating Hierarchy into Text Encoder: a Contrastive Learning Approach for Hierarchical Text Classification

Wang, Zihan; Wang, Peiyi; Huang, Lianzhe; Sun, Xingming; Wang, Houfeng

doi:10.18653/v1/2022.acl-long.491

Cited by 54 publications

(55 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In it, categories are treated in isolation (i.e., as having no relationship between one another) [15,16]. In contrast, HTC deals with documents whose labels are organized in structures that resemble a tree or a directed acyclic graph (DAG) [91,92]. In these structures, each node contains a label to be assigned, such as in Figure 6.…”

Section: Types Of Hierarchical Classificationmentioning

confidence: 99%

Hierarchical Text Classification and Its Foundations: A Review of Current Research

Zangari,

Marcuzzo,

Rizzo

et al. 2024

Electronics

View full text Add to dashboard Cite

While collections of documents are often annotated with hierarchically structured concepts, the benefits of these structures are rarely taken into account by classification techniques. Within this context, hierarchical text classification methods are devised to take advantage of the labels’ organization to boost classification performance. In this work, we aim to deliver an updated overview of the current research in this domain. We begin by defining the task and framing it within the broader text classification area, examining important shared concepts such as text representation. Then, we dive into details regarding the specific task, providing a high-level description of its traditional approaches. We then summarize recently proposed methods, highlighting their main contributions. We also provide statistics for the most commonly used datasets and describe the benefits of using evaluation metrics tailored to hierarchical settings. Finally, a selection of recent proposals is benchmarked against non-hierarchical baselines on five public domain-specific datasets. These datasets, along with our code, are made available for future research.

show abstract

Section: Types Of Hierarchical Classificationmentioning

confidence: 99%

Hierarchical Text Classification and Its Foundations: A Review of Current Research

Zangari,

Marcuzzo,

Rizzo

et al. 2024

Electronics

View full text Add to dashboard Cite

show abstract

“…For example, "tumor" was converted to "An H&E image of tumor". As a natural comparison on the zero-shot task, we compared PLIP with the original CLIP model, which has been frequently used for other medical image tasks [31][32][33] and has already been trained from other medical images. Our analysis showed that PLIP consistently outperformed the baseline CLIP model and the results from predicting the majority class (or Majority) (Figure 2c).…”

Section: Plip Can Perform Zero-shot Classification On New Datamentioning

confidence: 99%

Leveraging medical Twitter to build a visual–language foundation model for pathology AI

Huang

Bianchi

Yüksekgönül

et al. 2023

Preprint

View full text Add to dashboard Cite

The lack of annotated publicly available medical images is a major barrier for innovations. At the same time, many de-identified images and much knowledge are shared by clinicians on public forums such as medical Twitter. Here we harness these crowd platforms to curate OpenPath, a large dataset of 208,414 pathology images paired with natural language descriptions. This is the largest public dataset for pathology images annotated with natural text. We demonstrate the value of this resource by developing PLIP, a multimodal AI with both image and text understanding, which is trained on OpenPath. PLIP achieves state-of-the-art zero-shot and transfer learning performances for classifying new pathology images across diverse tasks. Moreover, PLIP enables users to retrieve similar cases by either image or natural language search, greatly facilitating knowledge sharing. Our approach demonstrates that publicly shared medical information is a tremendous resource that can be harnessed to advance biomedical AI.

show abstract

“…This approach uses the relationships between labels in the hierarchy to regularize the model and prevent overfitting. Furthermore, as the hierarchical multi-label classification task corresponds to the relationships among labels stored in the hierarchy, an increasing number of studies are considering not only the information provided by the classification target but also the corresponding representation of the hierarchical structure of labels [ 25 , 26 ]. These methods assign varying weights to distinct parts of the content representation that are the most associated with each label in the hierarchy, taking into account the interdependence between the representation of the hierarchical structure and the classification target.…”

Section: Related Workmentioning

confidence: 99%

Multi-Label Classification in Anime Illustrations Based on Hierarchical Attribute Relationships

Lan

Maeda

Ogawa

et al. 2023

Sensors

View full text Add to dashboard Cite

In this paper, we propose a hierarchical multi-modal multi-label attribute classification model for anime illustrations using a graph convolutional network (GCN). Our focus is on the challenging task of multi-label attribute classification, which requires capturing subtle features intentionally highlighted by creators of anime illustrations. To address the hierarchical nature of these attributes, we leverage hierarchical clustering and hierarchical label assignments to organize the attribute information into a hierarchical feature. The proposed GCN-based model effectively utilizes this hierarchical feature to achieve high accuracy in multi-label attribute classification. The contributions of the proposed method are as follows. Firstly, we introduce GCN to the multi-label attribute classification task of anime illustrations, enabling the capturing of more comprehensive relationships between attributes from their co-occurrence. Secondly, we capture subordinate relationships among the attributes by adopting hierarchical clustering and hierarchical label assignment. Lastly, we construct a hierarchical structure of attributes that appear more frequently in anime illustrations based on certain rules derived from previous studies, which helps to reflect the relationships between different attributes. The experimental results on multiple datasets show that the proposed method is effective and extensible by comparing it with some existing methods, including the state-of-the-art method.

show abstract

Incorporating Hierarchy into Text Encoder: a Contrastive Learning Approach for Hierarchical Text Classification

Cited by 54 publications

References 24 publications

Hierarchical Text Classification and Its Foundations: A Review of Current Research

Hierarchical Text Classification and Its Foundations: A Review of Current Research

Leveraging medical Twitter to build a visual–language foundation model for pathology AI

Multi-Label Classification in Anime Illustrations Based on Hierarchical Attribute Relationships

Contact Info

Product

Resources

About