# Constrained Sequence-to-Tree Generation for Hierarchical Text Classification

arXiv: https://arxiv.org/abs/2204.00811 · HTML: https://mlsanity.com/paper/2204.00811/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 25 references that are in the map.
- First posted on arXiv 2 Apr 2022.

## Builds on (most cited first, 12 of 12)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [Structured Prediction as Translation between Augmented Natural Languages](https://mlsanity.com/paper/2101.05779/) (2021)
- [HDLTex: Hierarchical Deep Learning for Text Classification](https://mlsanity.com/paper/1709.08267/) (2017)
- [SGM: Sequence Generation Model for Multi-label Classification](https://mlsanity.com/paper/1806.04822/) (2018)
- [Grammar as a Foreign Language](https://mlsanity.com/paper/1412.7449/) (2014)
- [Hierarchical Text Classification with Reinforced Label Assignment](https://mlsanity.com/paper/1908.10419/) (2019)
- [Paradigm Shift in Natural Language Processing](https://mlsanity.com/paper/2109.12575/) (2021)
- [HTCInfoMax: A Global Model for Hierarchical Text Classification via Information Maximization](https://mlsanity.com/paper/2104.05220/) (2021)
- [Neural Fine-Grained Entity Type Classification with Hierarchy-Aware Loss](https://mlsanity.com/paper/1803.03378/) (2018)
- [A Tree-based Decoder for Neural Machine Translation](https://mlsanity.com/paper/1808.09374/) (2018)
- [Joint Learning of Hyperbolic Label Embeddings for Hierarchical Multi-label Classification](https://mlsanity.com/paper/2101.04997/) (2021)

## Built on by (most cited first, 13 of 13)

- [Hierarchical Verbalizer for Few-Shot Hierarchical Text Classification](https://mlsanity.com/paper/2305.16885/) (2023)
- [Revisiting Hierarchical Text Classification: Inference and Metrics](https://mlsanity.com/paper/2410.01305/) (2024)
- [HiGen: Hierarchy-Aware Sequence Generation for Hierarchical Text Classification](https://mlsanity.com/paper/2402.01696/) (2024)
- [G2PTL: A Pre-trained Model for Delivery Address and its Applications in Logistics System](https://mlsanity.com/paper/2304.01559/) (2023)
- [Instances and Labels: Hierarchy-aware Joint Supervised Contrastive Learning for Hierarchical Multi-Label Text Classification](https://mlsanity.com/paper/2310.05128/) (2023)
- [Analyzing Persuasive Strategies in Meme Texts: A Fusion of Language Models with Paraphrase Enrichment](https://mlsanity.com/paper/2407.01784/) (2024)
- [Domain-Hierarchy Adaptation via Chain of Iterative Reasoning for Few-shot Hierarchical Text Classification](https://mlsanity.com/paper/2407.08959/) (2024)
- [HCRE: LLM-based Hierarchical Classification for Cross-Document Relation Extraction with a Prediction-then-Verification Strategy](https://mlsanity.com/paper/2604.07937/) (2026)
- [Are We Really Making Much Progress in Text Classification? A Comparative Review](https://mlsanity.com/paper/2204.03954/) (2022)
- [A Transformer-based Autoregressive Decoder Architecture for Hierarchical Text Classification](https://mlsanity.com/paper/2501.13598/) (2025)
- [Taxon: Hierarchical Tax Code Prediction with Semantically Aligned LLM Expert Guidance](https://mlsanity.com/paper/2601.08418/) (2026)
- [FEAST: Retrieval-Augmented Multi-Hierarchical Food Classification for the FoodEx2 System](https://mlsanity.com/paper/2603.03176/) (2026)
- [SCHK-HTC: Sibling Contrastive Learning with Hierarchical Knowledge-Aware Prompt Tuning for Hierarchical Text Classification](https://mlsanity.com/paper/2604.15998/) (2026)

## Abstract (arXiv)

Hierarchical Text Classification (HTC) is a challenging task where a document can be assigned to multiple hierarchically structured categories within a taxonomy. The majority of prior studies consider HTC as a flat multi-label classification problem, which inevitably leads to "label inconsistency" problem. In this paper, we formulate HTC as a sequence generation task and introduce a sequence-to-tree framework (Seq2Tree) for modeling the hierarchical label structure. Moreover, we design a constrained decoding strategy with dynamic vocabulary to secure the label consistency of the results. Compared with previous works, the proposed approach achieves significant and consistent improvements on three benchmark datasets.