SGM: Sequence Generation Model for Multi-label Classification

By Pengcheng Yang, Xu Sun, Wei Li, Shuming Ma, Wei Wu, Houfeng Wang. 2018

434 citations recorded by the source corpus.

Multi-label classification is an important yet challenging task in natural language processing. It is more complex than single-label classification in that the labels tend to be correlated. Existing methods tend to ignore the correlations between labels. Besides, different parts of the text can contribute differently for predicting different labels, which is not considered by existing models. In this paper, we propose to view the multi-label classification task as a sequence generation problem, and apply a sequence generation model with a novel decoder structure to solve it. Extensive experimental results show that our proposed methods outperform previous work by a substantial margin. Further analysis of experimental results demonstrates that the proposed methods not only capture the correlations between labels, but also select the most informative words automatically when predicting different labels.

Subfields: Artificial Intelligence

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

Citations in the corpus

Memory Efficient Continual Learning with Transformers (2022, methodology): “We use three text datasets for multi-label text classiﬁcation: Arxiv Papers [66] (paper classiﬁcation), Reuters (RCV1-V2) [29] (news classiﬁcation), Wiki-30K [71] (Wikipedia article classiﬁcation) and two dataset for image classiﬁcation: CIFAR100 [28] and MiniImageNet [49].”
Memory Efficient Continual Learning for Neural Text Classification (2022, methodology): “For Arxiv Papers and Reuters datasets, we created 20 tasks and for Wiki-30K dataset we created 60 tasks and we ﬁxed the number of samples per tasks to 100 for the training set.”
A Survey on Text Classification: From Shallow to Deep Learning (2020, background): “…Accuracy SNLI cross-attention mechanism [129] F1 WebQuestion self-attention sentence embedding [130] Accuracy Yelp, Age sequence generation model [74] HL, M icro − F 1 RCV1-V2, AAPD deep contextualized representation [66] Accuracy, F1 SQuAD, SNLI, SRL, SST-5, etc. a label tree-based model [131]…”
AttentionXML: Label Tree-based Attention-Aware Deep Model for High-Performance Extreme Multi-Label Text Classification (2018, methodology): “Another type of deep learning-based methods is sequence-to-sequence (Seq2Seq) learning-based methods, such as MLC2Seq [21], SGM [29] and SU4MLC [15].”
A Survey on Text Classification: From Traditional to Deep Learning (2020, background): “The SICK contains almost 10,000 English sentence pairs.”
A Dual Reinforcement Learning Framework for Unsupervised Text Style Transfer (2019, background): “[ Shen et al. , 2017; Hu et al. , 2017; Yang et al. , 2018b ] combine Variational Auto-encoder (VAE) with a style discriminator.”
Description Based Text Classification with Reinforcement Learning (2020, neutral): “We use the splits provided by Yang et al. (2018).”
DocBERT: BERT for Document Classification (2019, methodology): “, 1994), arXiv Academic Paper dataset (AAPD; Yang et al., 2018), IMDB reviews, and Yelp 2014 reviews.”