# Semantic-Unit-Based Dilated Convolution for Multi-Label Text Classification

arXiv: https://arxiv.org/abs/1808.08561 · HTML: https://mlsanity.com/paper/1808.08561/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Aug 2018.

## Built on by (most cited first, 8 of 8)

- [An Effective Deployment of Contrastive Learning in Multi-label Text Classification](https://mlsanity.com/paper/2212.00552/) (2022)
- [KenMeSH: Knowledge-enhanced End-to-end Biomedical Text Labelling](https://mlsanity.com/paper/2203.06835/) (2022)
- [Auxiliary Knowledge-Induced Learning for Automatic Multi-Label Medical Document Classification](https://mlsanity.com/paper/2405.19084/) (2024)
- [Dual-Decoupling Learning and Metric-Adaptive Thresholding for Semi-Supervised Multi-Label Learning](https://mlsanity.com/paper/2407.18624/) (2024)
- [MeSHup: A Corpus for Full Text Biomedical Document Indexing](https://mlsanity.com/paper/2204.13604/) (2022)
- [The Master-Slave Encoder Model for Improving Patent Text Summarization: A New Approach to Combining Specifications and Claims](https://mlsanity.com/paper/2411.14072/) (2024)
- [KeNet:Knowledge-enhanced Doc-Label Attention Network for Multi-label text classification](https://mlsanity.com/paper/2403.01767/) (2024)
- [A Debiased Nearest Neighbors Framework for Multi-Label Text Classification](https://mlsanity.com/paper/2408.03202/) (2024)

## Abstract (arXiv)

We propose a novel model for multi-label text classification, which is based on sequence-to-sequence learning. The model generates higher-level semantic unit representations with multi-level dilated convolution as well as a corresponding hybrid attention mechanism that extracts both the information at the word-level and the level of the semantic unit. Our designed dilated convolution effectively reduces dimension and supports an exponential expansion of receptive fields without loss of local information, and the attention-over-attention mechanism is able to capture more summary relevant information from the source context. Results of our experiments show that the proposed model has significant advantages over the baseline models on the dataset RCV1-V2 and Ren-CECps, and our analysis demonstrates that our model is competitive to the deterministic hierarchical models and it is more robust to classifying low-frequency labels.