Hierarchy-Aware Global Model for Hierarchical Text Classification

Due to the complex label hierarchy and intensive labeling cost in practice, the hierarchical text classification (HTC) suffers a poor performance especially when low-resource or few-shot settings are considered. Recently, there is a growing trend of applying prompts on pre-trained language models (PLMs), which has exhibited effectiveness in the few-shot flat text classification tasks. However, limited work has studied the paradigm of prompt-based learning in the HTC problem when the training data is extremely scarce. In this work, we define a path-based few-shot setting and establish a strict path-based evaluation metric to further explore few-shot HTC tasks. To address the issue, we propose the hierarchical verbalizer (“HierVerb”), a multi-verbalizer framework treating HTC as a single- or multi-label classification problem at multiple layers and learning vectors as verbalizers constrained by hierarchical structure and hierarchical contrastive learning. In this manner, HierVerb fuses label hierarchy knowledge into verbalizers and remarkably outperforms those who inject hierarchy through graph encoders, maximizing the benefits of PLMs. Extensive experiments on three popular HTC datasets under the few-shot settings demonstrate that prompt with HierVerb significantly boosts the HTC performance, meanwhile indicating an elegant way to bridge the gap between the large pre-trained model and downstream hierarchical classification tasks.

Hierarchy-Aware and Label Balanced Model for Hierarchical Text Classification

Computer Vision has become the poster child for Deep Learning. The image classification accuracy of convolutional neural nets on benchmark data sets has increased every year since their inception. This has been aided with advances in feature fusion. The increase in the availability of imagetext occurrence has lead to text augmented feature spaces that have lead to higher accuracy in in image classification tasks. However, these works are limited to instances where text is readily available. This study presents an approach to featurize text within natural images with the goal of augmenting image features for image classification tasks. Text extraction and featurization in natural images is a challenging task due to challenges in reliable text localization and OCR results, both being impeded by the variability in image text and errors in OCR. We overcome these challenges by implementing a novel bounding box concatenation algorithm and a novel feature boosting algorithm. The result is a pipeline that encodes an image into a text feature space. Classifiers trained on the text based feature space have comparable accuracy to the state of the art Convolutional Neural Nets (CNN's) while being significantly inexpensive computationally. Moreover, the augmentation of text features to image features generates a hybrid feature space with a higher information content for a classification problem when compared to a feature space comprised exclusively of image features. Thus, we see a rise in classification accuracy across all state of the art machine learning algorithms.

Hierarchical text classification concerning the relationship among categories has become an interesting problem recently. Most research has focused on tree-structured categories, but in reality directed acyclic graph (DAG) – structured categories, where a child category may have more than one parent category, appear more often. In this paper, we introduce three approaches, namely, flat, tree-based, and DAG-based, for solving the multi-label text classification problem in which categories are organized as a DAG, and documents are classified into both leaf and internal categories. We also present experimental results of the methods using SVMs as classifiers on the Reuters-21578 collection and our data set of research papers in Artificial Intelligence.Keywordstext classificationhierarchiesmulti-labelsSVM

Hierarchical multi-label text classification (HMTC) has become rather challenging when it requires handling large sets of closely related categories. We present a novel software that provides a hybrid embedding-based text representation for HMTC, shortened as HE-HMTC. It made full use of categories’ structure and their labels semantics to enrich the text representation, and therefore attempted to improve the classification performance of the text. In addition, HE-HMTC facilitates improving the accuracy of HMTC tasks. Moreover, our HE-HMTC can easily be generalized in other hierarchical classification tasks and achieve superior performance.

Although an improvement of hierarchical text classification can be achieved by using hierarchical structure information, existing hierarchical text classification methods suffer from two problems: data skew (especially in large-scale hierarchy) and error propagation. In this paper, we first define the concept of path-based semantic vector for the presentation of categories. Then a set of additional reliable training data for data-sparse categories can be retrieved based on such representation and particular similarity metrics. This training data enhancement strategy is classifier independent and can improve the classification of categories without adequate training data. Second, we propose the occurrence probability based strategy for hierarchical text classification which can reduce error propagation efficiently. Cooccurrence probability is then introduced to correct the errors occurred on higher levels of the hierarchy. Extensive experiments show that our hierarchical classification strategies perform well on ODP dataset, even in the condition of having few training data.

This study aimed to develop a classification model to detect and distinguish apathy and depression based on text, audio, and video features and to make use of the shapely additive explanations (SHAP) toolkit to increase the model interpretability. Subjective scales and objective experiments were conducted on 319 mild cognitive impairment (MCI) patients to measure apathy and depression. The MCI patients were classified into four groups, depression only, apathy only, depressed-apathetic, and the normal group. Speech, facial and text features were extracted using the open-source data analysis toolkits. Multiclass classification and SHAP toolkits were used to develop a classification model and explain the contribution of specific features. The macro-averaged f1 score and accuracy for overall model were 0.91 and 0.90, respectively. The accuracy for the apathetic, depressed, depressed-apathetic, and normal groups were 0.98, 0.88, 0.93, and 0.82, respectively. The SHAP toolkit identified speech features (Mel-frequency cepstral coefficient (MFCC) 4, spectral slopes, F0, F1), facial features (action unit (AU) 14, 26, 28, 45), and text feature (text 6 semantic) associated with apathy. Meanwhile, speech features (spectral slopes, shimmer, F0) and facial expression (AU 2, 6, 7, 10, 14, 26, 45) were associated with depression. Apart from the shared features mentioned above, new speech (MFCC 2, loudness) and facial (AU 9) features were observed in the depressive-apathetic group. Apathy and depression shared some verbal and facial features while also exhibited distinct features. A combination of text, audio, and video could be used to improve the early detection and differential diagnosis of apathy and depression in MCI patients.

Hierarchical GAN-Tree and Bi-Directional Capsules for multi-label image classification

This paper presents an investigation into the summarisation of the free text element of questionnaire data using hierarchical text classification. The process makes the assumption that text summarisation can be achieved using a classification approach whereby several class labels can be associated with documents which then constitute the summarisation. A hierarchical classification approach is suggested which offers the advantage that different levels of classification can be used and the summarisation customised according to which branch of the tree the current document is located. The approach is evaluated using free text from questionnaires used in the SAVSNET (Small Animal Veterinary Surveillance Network) project. The results demonstrate the viability of using hierarchical classification to generate free text summaries.

Hierarchical classification has been becoming a popular research topic nowadays, particularly on the web as text categorization. For a large web corpus, there can be a hierarchy with hundreds of thousands of topics, so it is common to handle this task using a flat classification approach, inducing a binary classifier only for the leaf-node classes. However, it always suffers from such low prediction accuracy due to an imbalanced issue in the training data. In this paper, we propose two novel strategies: (i) “Top-Level Pruning” to narrow down the candidate classes, and (ii) “Exclusive Top-Level Training Policy” to build more effective classifiers by utilizing the top-level data. The experiments on the Wikipedia dataset show that our system outperforms the traditional flat approach unanimously on all hierarchical classification metrics.

Owing to the inherent limitations of convolutional neural networks (CNNs), text classification has historically fallen short of the performance achieved by 2D CNNs in computer vision. Furthermore, the intrinsic complexity and variability of textual data make shallow classification models insufficient for capturing deeper and more abstract semantic representations. To overcome these challenges, this study adopts a constrained 2D CNN coupled with a vision-inspired attention mechanism to extract informative textual features, thereby constructing a novel representation termed a multi-scale textual feature map. Building on the demonstrated effectiveness of ResNet and SENet in deep architectures, we further designed a competitive attention mechanism specifically tailored for multi-scale textual feature maps and introduced the Deep 2D CNN (D3CNN). Experimental results indicate that D3CNN yields substantial performance improvements over baseline models across five benchmark datasets, approaching the accuracy of state-of-the-art Transformer-based architectures while maintaining a favorable balance between performance and computational efficiency.

As one of the most popular social media platforms, microblogs are ideal places for news propagation. In microblogs, tweets with both text and images are more likely to attract attention than text-only tweets. This advantage is exploited by fake news producers to publish fake news, which has a devasting impact on individuals and society. Thus, multimodal fake news detection has attracted the attention of many researchers. For news with text and image, multimodal fake news detection utilizes both text and image information to determine the authenticity of news. Most of the existing methods for multimodal fake news detection obtain a joint representation by simply concatenating a vector representation of the text and a visual representation of the image, which ignores the dependencies between them. Although there are a small number of approaches that use the attention mechanism to fuse them, they are not fine-grained enough in feature fusion. The reason is that, for a given image, there are multiple visual features and certain correlations between these features. They do not use multiple feature vectors representing different visual features to fuse with textual features, and ignore the correlations, resulting in inadequate fusion of textual features and visual features. In this paper, we propose a novel fine-grained multimodal fusion network (FMFN) to fully fuse textual features and visual features for fake news detection. Scaled dot-product attention is utilized to fuse word embeddings of words in the text and multiple feature vectors representing different features of the image, which not only considers the correlations between different visual features but also better captures the dependencies between textual features and visual features. We conduct extensive experiments on a public Weibo dataset. Our approach achieves competitive results compared with other methods for fusing visual representation and text representation, which demonstrates that the joint representation learned by the FMFN (which fuses multiple visual features and multiple textual features) is better than the joint representation obtained by fusing a visual representation and a text representation in determining fake news.

We present work on deception detection, where, given a spoken claim, we aim to predict its factuality. While previous work in the speech community has relied on recordings from staged setups where people were asked to tell the truth or to lie and their statements were recorded, here we use real-world political debates. Thanks to the efforts of fact-checking organizations, it is possible to obtain annotations for statements in the context of a political discourse as true, half-true, or false. Starting with such data from the CLEF-2018 CheckThat! Lab, which was limited to text, we performed alignment to the corresponding videos, thus producing a multimodal dataset. We further developed a multimodal deep-learning architecture for the task of deception detection, which yielded sizable improvements over the state of the art for the CLEF-2018 Lab task 2. Our experiments show that the use of the acoustic signal consistently helped to improve the performance compared to using textual and metadata features only, based on several different evaluation measures. We release the new dataset to the research community, hoping to help advance the overall field of multimodal deception detection.

Automated radiographic report generation is challenging in at least two aspects. First, medical images are very similar to each other and the visual differences of clinic importance are often fine-grained. Second, the disease-related words may be submerged by many similar sentences describing the common content of the images, causing the abnormal to be misinterpreted as the normal in the worst case. To tackle these challenges, this paper proposes a pure transformer-based framework to jointly enforce better visual-textual alignment, multi-label diagnostic classification, and word importance weighting, to facilitate report generation. To the best of our knowledge, this is the first pure transformer-based framework for medical report generation, which enjoys the capacity of transformer in learning long range dependencies for both image regions and sentence words. Specifically, for the first challenge, we design a novel mechanism to embed an auxiliary image-text matching objective into the transformer's encoder-decoder structure, so that better correlated image and text features could be learned to help a report to discriminate similar images. For the second challenge, we integrate an additional multi-label classification task into our framework to guide the model in making correct diagnostic predictions. Also, a term-weighting scheme is proposed to reflect the importance of words for training so that our model would not miss key discriminative information. Our work achieves promising performance over the state-of-the-arts on two benchmark datasets, including the largest dataset MIMIC-CXR.

Web document hierarchical classification approaches often rely on textual features alone even though web pages include multimedia data. We propose a new hierarchical integrated web classification approach that combines image-based and text-based approaches. Instead of using a flat classifier to combine text and image classification, we perform classification on a hierarchy differently on different levels of the tree, using text for branches and images only at leaves. The results of our experiments show that the use of the hierarchical structure improved web document classification performance significantly.