# Hierarchical Text Classification As Sub-Hierarchy Sequence Generation

arXiv: https://arxiv.org/abs/2111.11104 · HTML: https://mlsanity.com/paper/2111.11104/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 36 references that are in the map.
- First posted on arXiv 22 Nov 2021.

## Builds on (most cited first, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [Do Transformers Really Perform Bad for Graph Representation?](https://mlsanity.com/paper/2106.05234/) (2021)
- [Explainable Prediction of Medical Codes from Clinical Text](https://mlsanity.com/paper/1802.05695/) (2018)
- [HDLTex: Hierarchical Deep Learning for Text Classification](https://mlsanity.com/paper/1709.08267/) (2017)
- [Large-Scale Multi-Label Text Classification on EU Legislation](https://mlsanity.com/paper/1906.02192/) (2019)
- [SGM: Sequence Generation Model for Multi-label Classification](https://mlsanity.com/paper/1806.04822/) (2018)
- [Hierarchical Text Classification with Reinforced Label Assignment](https://mlsanity.com/paper/1908.10419/) (2019)
- [Learning to Learn and Predict: A Meta-Learning Approach for Multi-Label Classification](https://mlsanity.com/paper/1909.04176/) (2019)
- [Hierarchical Taxonomy-Aware and Attentional Graph Capsule RCNNs for Large-Scale Multi-Label Text Classification](https://mlsanity.com/paper/1906.04898/) (2019)
- [HTCInfoMax: A Global Model for Hierarchical Text Classification via Information Maximization](https://mlsanity.com/paper/2104.05220/) (2021)
- [Investigating Capsule Networks with Dynamic Routing for Text Classification](https://mlsanity.com/paper/1804.00538/) (2018)

## Built on by (most cited first, 6 of 6)

- [Retrieval-style In-Context Learning for Few-shot Hierarchical Text Classification](https://mlsanity.com/paper/2406.17534/) (2024)
- [LH-Mix: Local Hierarchy Correlation Guided Mixup over Hierarchical Prompt Tuning](https://mlsanity.com/paper/2412.16963/) (2024)
- [Taxon: Hierarchical Tax Code Prediction with Semantically Aligned LLM Expert Guidance](https://mlsanity.com/paper/2601.08418/) (2026)
- [Leveraging Weighted Syntactic and Semantic Context Assessment Summary (wSSAS) Towards Text Categorization Using LLMs](https://mlsanity.com/paper/2604.12049/) (2026)
- [Consistency Analysis of Sentiment Predictions using Syntactic & Semantic Context Assessment Summarization (SSAS)](https://mlsanity.com/paper/2604.15547/) (2026)
- [How to Estimate Whether You Have Found Several Needles in a Haystack: Measuring Calibration in Multi-Label Text Classification](https://mlsanity.com/paper/2609.26468/) (2026)

## Abstract (arXiv)

Hierarchical text classification (HTC) is essential for various real applications. However, HTC models are challenging to develop because they often require processing a large volume of documents and labels with hierarchical taxonomy. Recent HTC models based on deep learning have attempted to incorporate hierarchy information into a model structure. Consequently, these models are challenging to implement when the model parameters increase for a large-scale hierarchy because the model structure depends on the hierarchy size. To solve this problem, we formulate HTC as a sub-hierarchy sequence generation to incorporate hierarchy information into a target label sequence instead of the model structure. Subsequently, we propose the Hierarchy DECoder (HiDEC), which decodes a text sequence into a sub-hierarchy sequence using recursive hierarchy decoding, classifying all parents at the same level into children at once. In addition, HiDEC is trained to use hierarchical path information from a root to each leaf in a sub-hierarchy composed of the labels of a target document via an attention mechanism and hierarchy-aware masking. HiDEC achieved state-of-the-art performance with significantly fewer model parameters than existing models on benchmark datasets, such as RCV1-v2, NYT, and EURLEX57K.