A Deep Reinforced Sequence-to-Set Model for Multi-Label Classification

Yang, Pengcheng; Luo, Fuli; Ma, Shuming; Lin, Junyang; Sun, Xu

doi:10.18653/v1/p19-1518

Cited by 110 publications

(196 citation statements)

References 33 publications

(47 reference statements)

Supporting

Mentioning

185

Contrasting

Order By: Relevance

“…The AAPD dataset (P. Yang, Sun, et al, 2018) contains a combination of 55,840 pairs of abstracts and corresponding multilabel subject classifications. Tags cover 54 types of labels.…”

Section: Experimental Datasetmentioning

confidence: 99%

Uncertainty quantification for multilabel text classification

Chen

Zhang

2020

WIREs Data Min & Knowl

View full text Add to dashboard Cite

Deep neural networks have recently achieved impressive performance on multilabel text classification. However, the uncertainty in multilabel text classification tasks and their application in the model are often overlooked. To better understand and evaluate the uncertainty in multilabel text classification tasks, we propose a general framework called Uncertainty Quantification for Multilabel Text Classification framework. Based on the prediction results produced by traditional neural networks, the aleatory uncertainty of each classification label and the epistemic uncertainty of the prediction result can further be obtained by this framework. We design experiments to characterize the properties of aleatory uncertainty and epistemic uncertainty from the data characteristics and model features. The experimental results show that this framework is reasonable. Furthermore, we demonstrate how this framework allows us to define the model optimization criterion to identify policies that balance the expected training cost, model performance, and uncertainty sensitivity.

show abstract

“…The AAPD dataset (P. Yang, Sun, et al, 2018) contains a combination of 55,840 pairs of abstracts and corresponding multilabel subject classifications. Tags cover 54 types of labels.…”

Section: Experimental Datasetmentioning

confidence: 99%

Uncertainty quantification for multilabel text classification

Chen

Zhang

2020

WIREs Data Min & Knowl

View full text Add to dashboard Cite

show abstract

“…However, the above methods ignore the association between labels. In recent years, there has been work on making use of the association relationship between labels, which applies the sequence generation method into multi-label classification [2], [19]- [22].…”

Section: B Multi-label Text Classificationmentioning

confidence: 99%

“…SGM [22] multi-label classification: The Seq2Seq model with attention mechanism is used for multi-label text classification. Besides, the concept of ''global embedding'' is introduced, in which labels except the one with the maximum probability at the previous time step are used together for the prediction of the labels at the current time step.…”

Section: Baselinementioning

confidence: 99%

Generative Multi-Task Learning for Text Classification

et al. 2020

View full text Add to dashboard Cite

Multi-task learning leverages potential correlations among related tasks to extract common features and yield performance gains. In this paper, a generative multi-task learning (MTL) approach for text classification and categorization is proposed, which is composed of a shared encoder, a multilabel classification decoder and a hierarchical categorization decoder. In the two decoders, a label-orderindependent multi-label classification loss function and a hierarchical structure mask matrix are introduced. Experiments conducted on the real-world public security dataset show that the proposed approach has obvious advantages over the baseline approaches and can enhance the semantic association between the results of the classification and categorization tasks. INDEX TERMS Generative model, hierarchical classification, multi-label classification, multi-task learning.

show abstract

“…Nam et al [14] used Seq2Seq architecture with GRU encoder and attention-based GRU decoder, achieving an improvement over a standard GRU model [3] on several datasets and metrics. Yang et al [29] continued this idea by introducing Sequence Generation Model (SGM) consisting of BiLSTM-based encoder and LSTM decoder [6] coupled with additive attention mechanism [2].…”

Section: Introductionmentioning

confidence: 99%

BERT for Sequence-to-Sequence Multi-label Text Classification

Yarullin

Serdyukov

2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

We study the BERT language representation model and the sequence generation model with BERT encoder for the multi-label text classification task. We show that the Sequence Generating BERT model achieves decent results in significantly fewer training epochs compared to the standard BERT. We also introduce and experimentally examine a mixed model, an ensemble of BERT and Sequence Generating BERT models. Our experiments demonstrate that the proposed model outperforms current baselines in several metrics on three well-studied multilabel classification datasets with English texts and two private Yandex Taxi datasets with Russian texts.

show abstract

A Deep Reinforced Sequence-to-Set Model for Multi-Label Classification

Cited by 110 publications

References 33 publications

Uncertainty quantification for multilabel text classification

Uncertainty quantification for multilabel text classification

Generative Multi-Task Learning for Text Classification

BERT for Sequence-to-Sequence Multi-label Text Classification

Contact Info

Product

Resources

About