XRR: Extreme multi-label text classification with candidate retrieving and deep ranking

Xiong, Jie; Yu, Li; Niu, Xi; Leng, Youfang

doi:10.1016/j.ins.2022.11.158

Cited by 25 publications

(7 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The extracted features with dimension d = 128 are later combined with the key features and fed to the ML model for classification. The feature extraction layer uses the GELU [69] as a non-linear activation function to improve the model's performance, defined as in Eq. (1).…”

Section: Pre-processing Of Main Features (Key Features)mentioning

confidence: 99%

Terrorism Attack Classification Using Machine Learning: The Effectiveness of Using Textual Features Extracted from GTD Dataset

Abdalsalam,

Li,

Dahou

et al. 2024

CMES

View full text Add to dashboard Cite

One of the biggest dangers to society today is terrorism, where attacks have become one of the most significant risks to international peace and national security. Big data, information analysis, and artificial intelligence (AI) have become the basis for making strategic decisions in many sensitive areas, such as fraud detection, risk management, medical diagnosis, and counter-terrorism. However, there is still a need to assess how terrorist attacks are related, initiated, and detected. For this purpose, we propose a novel framework for classifying and predicting terrorist attacks. The proposed framework posits that neglected text attributes included in the Global Terrorism Database (GTD) can influence the accuracy of the model's classification of terrorist attacks, where each part of the data can provide vital information to enrich the ability of classifier learning. Each data point in a multiclass taxonomy has one or more tags attached to it, referred as "related tags." We applied machine learning classifiers to classify terrorist attack incidents obtained from the GTD. A transformer-based technique called DistilBERT extracts and learns contextual features from text attributes to acquire more information from text data. The extracted contextual features are combined with the "key features" of the dataset and used to perform the final classification. The study explored different experimental setups with various classifiers to evaluate the model's performance. The experimental results show that the proposed framework outperforms the latest techniques for classifying terrorist attacks with an accuracy of 98.7% using a combined feature set and extreme gradient boosting classifier.

show abstract

Section: Pre-processing Of Main Features (Key Features)mentioning

confidence: 99%

Terrorism Attack Classification Using Machine Learning: The Effectiveness of Using Textual Features Extracted from GTD Dataset

Abdalsalam,

Li,

Dahou

et al. 2024

CMES

View full text Add to dashboard Cite

show abstract

“…In [31], the XMTC task is tackled by a hybrid approach, which leverages two stages. The first one is devoted to the retrieval task and exploits two approaches, a Point Mutual Information method and a Unified Label-Semantic Embedding method, to the end of extracting hundreds of candidate labels from a huge label set.…”

Section: Related Workmentioning

confidence: 99%

Integrating PubMed Label Hierarchy Knowledge into a Complex Hierarchical Deep Neural Network

Silvestri,

Gargiulo,

Ciampi

2023

Applied Sciences

View full text Add to dashboard Cite

This paper proposes an innovative method that exploits a complex deep learning network architecture, called Hierarchical Deep Neural Network (HDNN), specifically developed for the eXtreme Multilabel Text Classification (XMTC) task, when the label set is hierarchically organized, such as the case of the PubMed article labeling task. In detail, the topology of the proposed HDNN architecture follows the exact hierarchical structure of the label set to integrate this knowledge directly into the DNN. We assumed that if a label set hierarchy is available, as in the case of the PubMed Dataset, forcing this information into the network topology could enhance the classification performances and the interpretability of the results, especially related to the hierarchy. We performed an experimental assessment of the PubMed article classification task, demonstrating that the proposed HDNN provides performance improvement for a baseline based on a classic flat Convolution Neural Network (CNN) deep learning architecture, in particular in terms of hierarchical measures. These results provide useful hints for integrating previous and innate knowledge in a deep neural network. The drawback of the HDNN is the high computational time required to train the neural network, which can be addressed with a parallel implementation planned as a future work.

show abstract

“…Poucos trabalhos recentes abordam marginalmente o desafio da desbalanceamento, como o AttentionXML, ao representar um texto dado de forma diferente para cada rótulo, o que é especialmente útil para muitos rótulos tail. XRR [Xiong et al 2023] emprega um framework com baseado em informac ¸ão mútua alinhada (aPMI) para capturar a coocorrência de termos de texto e rótulos, o que pode ser um esforc ¸o em relac ¸ão ao desafio da qualidade. No entanto, o XRR possui alto custo computacional para calcular o aPMI na etapa de inferência.…”

Section: Revisão Da Literaturaunclassified

Repense, Recupere e Reranqueie: Um Pipeline de Recuperação e Reranqueamento para Classificação de Texto Multi-rótulo Extrema

França,

Ribeiro-Neto,

Gonçalves

2023

Anais Estendidos Do XXXVIII Simpósio Brasileiro De Banco De Dados (SBBD Estendido 2023)

View full text Add to dashboard Cite

Extreme multi-label text classification (XMTC) involves assigning relevant labels to text from a huge space of labels. Addressing the core challenges of XMTC (volume, imbalance and quality), we propose xCoRetriev, a two-stage pipeline migrating from a classification perspective to an information retrieval (IR) approach. We address the volume challenge by efficiently combining IR methods; we face the imbalance challenge by better capturing the text-label relationship and; we've improved quality by enriching tag names with pseudo-labels. Our results demonstrate the strengths of xCoRetriev when compared to baselines in terms of: (i) scalability for large spaces of labels and amount of text; (ii) effectiveness in the face of high imbalance, especially for predicting infrequent labels – with gains of up to 40% in MRR and NDCG –; and (iii) ability to handle poor quality annotated text and labels.

show abstract

XRR: Extreme multi-label text classification with candidate retrieving and deep ranking

Cited by 25 publications

References 37 publications

Terrorism Attack Classification Using Machine Learning: The Effectiveness of Using Textual Features Extracted from GTD Dataset

Terrorism Attack Classification Using Machine Learning: The Effectiveness of Using Textual Features Extracted from GTD Dataset

Integrating PubMed Label Hierarchy Knowledge into a Complex Hierarchical Deep Neural Network

Repense, Recupere e Reranqueie: Um Pipeline de Recuperação e Reranqueamento para Classificação de Texto Multi-rótulo Extrema

Contact Info

Product

Resources

About