EMNLP Findings2024
From Text Segmentation to Enhanced Representation Learning: A Novel Approach to Multi-Label Classification for Long Texts
Abstract
Multi-label text classification (MLTC) is an important task in the field of natural language processing. Most existing models rely on highquality text representations provided by pretrained language models (PLMs). They hence face the challenge of input length limitation caused by PLMs, when dealing with long texts. In light of this, we introduce a comprehensive approach to multi-label long text classification. We propose a text segmentation algorithm, which guarantees to produce the optimal segmentation, to address the issue of input length limitation caused by PLMs. We incorporate external knowledge, labels' co-occurrence relations, and attention mechanisms in representation learning to enhance both text and label representations. Our method's effectiveness is validated through extensive experiments on various MLTC datasets, unraveling the intricate correlations between texts and labels.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on6
- Big Bird: Transformers for Longer SequencesManzil Zaheer, Guru Guruganesh, Kumar Avinava Dubey, Joshua Ainslie et al.NeurIPS 2020 · 3,159 citations
- Reformer: The Efficient TransformerNikita Kitaev, Lukasz Kaiser, Anselm LevskayaICLR 2020 · 2,878 citations
- CogLTX: Applying BERT to Long TextsMing Ding, Chang Zhou, Hongxia Yang, Jie TangNeurIPS 2020 · 163 citations
- Enhancing Hierarchical Text Classification through Knowledge Graph IntegrationYe Liu, Kai Zhang, Zhenya Huang, Kehang Wang et al.ACL Findings 2023 · 26 citations
- Label-Specific Dual Graph Neural Network for Multi-Label Text ClassificationQianwen Ma, Chunyuan Yuan, Wei Zhou, Songlin HuACL 2021
Related papers
- Towards Better Representations for Multi-Label Text Classification with Multi-granularity InformationFangfang Li, Puzhen Su, Junwen Duan, Weidong XiaoEMNLP Findings 2023 · 3 citations
- Enhancing Label Correlation Feedback in Multi-Label Text Classification via Multi-Task LearningXiming Zhang, Qian-Wen Zhang, Zhao Yan, Ruifang Liu et al.ACL Findings 2021 · 44 citations
- Pretrained Generalized Autoregressive Model with Adaptive Probabilistic Label Clusters for Extreme Multi-label Text ClassificationHui Ye, Zhiyu Chen, Da-Han Wang, Brian D. DavisonICML 2020 · 57 citations
- Preserving Label Correlation for Multi-label Text Classification by Prototypical RegularizationsFanshuang Kong, Richong Zhang, Xiaohui Guo, Junfan Chen et al.WWW 2025 · 3 citations
- Structural Contrastive Representation Learning for Zero-shot Multi-label Text ClassificationTianyi Zhang, Zhaozhuo Xu, Tharun Medini, Anshumali ShrivastavaEMNLP Findings 2022 · 12 citations
