Deep Learning for Extreme Multi-label Text Classification

By Wei-Cheng Chang, Yuexin Wu, Yiming Yang. 2017

735 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

Citations in the corpus

Large-Scale Hierarchical Text Classification with Recursively Regularized Deep Graph-CNN (2018, methodology): “We compare with XML-CNN model [29] which considered multi-label text classification using simple CNN model originally applied to sentence classification [20] and Recurrent Convolutional Neural Network model (RCNN) [23].”
AttentionXML: Label Tree-based Attention-Aware Deep Model for High-Performance Extreme Multi-Label Text Classification (2018, methodology): “They can be categorized into the following four types: 1) 1-vs-All [3,4,30,31], 2) Embedding-based [7,27], 3) Instance [10,25] or label tree-based [11, 13, 24, 28]) and 4) Deep learning-based methods [17] (see Appendix for more descriptions on these methods).”
Sentiment Analysis Based on Deep Learning: A Comparative Study (2020, background): “[64] Extreme multilabel text classification XML-CNN RCV1, EUR-Lex, Amazon, and Wiki Capturing richer information from different regions of the document”
Memory Efficient Continual Learning for Neural Text Classification (2022, background): “Text classiﬁcation is a widely used technology powering a number of industrial applications from news tagging to semantic search (Ye et al., 2020; Liu et al., 2017).”
Large-Scale Multi-Label Text Classification on EU Legislation (2019, methodology): “…of the investigated methods is that they are unsuitable for Extreme Multi-Label Text Classification where there are hundreds of thousands of labels (Liu et al., 2017; Zhang et al., 9The approximate randomization tests detected no statistically significant difference in this case (p = 0.20).”
DocBERT: BERT for Document Classification (2019, background): “, 2014) and word2vec (Mikolov et al., 2013). Numerous literature surveys detail this historical neural progress: Young et al. (2018) describe a series of increasingly intricate neural NLP approaches, all of which follow the classical recipe of training on word embeddings of task-specific data.”
A Survey on Text Classification: From Shallow to Deep Learning (2020, background): “…Subj, etc. dynamic k-Max pooling [7] Accuracy MR, TREC, Twitter character-level [5] Error Rate AG, Yelp P, DBPedia, etc. preceding short texts [9] Accuracy DSTC 4, MRDA, SwDA extreme multi-label [120] P@k, DCG@k, etc. EUR-Lex, Wiki-30K, etc. CNN deep pyramid CNN [59] Error Rate AG, DBPedia, Yelp.”
The Emerging Trends of Multi-Label Learning (2020, methodology): “In addition, some deep learning methods are also developed for the Challenging MLC problems, such as Extreme MLC [31], [31], [32], [33], partial and weakly-supervised MLC [19], [23], [23], [34], MLC with unseen labels [35], [36], [36].”
Deep Learning--based Text Classification (2020, methodology): “[47] propose a new CNN-based model that makes two modifications to the architecture of Kim-CNN [46].”
A Survey on Text Classification: From Traditional to Deep Learning (2020, background): “The SICK contains almost 10,000 English sentence pairs.”
Towards Scalable and Reliable Capsule Networks for Challenging NLP Applications (2019, methodology): “1556 Zhang, 2014) and XML-CNN (Liu et al., 2017).”
ProtoSiTex: Learning Semi-Interpretable Prototypes for Multi-label Text Classification (2025, unknown): “Models based on CNNs and RNNs improved text representation learning [32], [33], while GCNs were introduced to explicitly capture label correlations [34].”