@inproceedings{zhang-etal-2024-text-segmentation,
    title = "From Text Segmentation to Enhanced Representation Learning: A Novel Approach to Multi-Label Classification for Long Texts",
    author = "Zhang, Wang  and
      Wang, Xin  and
      Wang, Qian  and
      Deng, Tao  and
      Wu, Xiaoru",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2024.findings-emnlp.402/",
    doi = "10.18653/v1/2024.findings-emnlp.402",
    pages = "6864--6873",
    abstract = "Multi-label text classification (MLTC) is an important task in the field of natural language processing. Most existing models rely on high-quality text representations provided by pre-trained 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."
}