mlsanityData to 14 Oct 2026

Constrained Sequence-to-Tree Generation for Hierarchical Text Classification

arXiv 2204.00811 ↗First posted 2 Apr 2022cs.CLcited by 13

Not on the map. Why?

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.

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

12 of 25 references.

References · 12

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  2. 2019When Does Label Smoothing Help?cited by 988
  3. 2021Structured Prediction as Translation between Augmented Natural Languagescited by 183
  4. 2017HDLTex: Hierarchical Deep Learning for Text Classificationcited by 106
  5. 2018SGM: Sequence Generation Model for Multi-label Classificationcited by 89
  6. 2014Grammar as a Foreign Languagecited by 70
  7. 2019Hierarchical Text Classification with Reinforced Label Assignmentcited by 41
  8. 2021Paradigm Shift in Natural Language Processingcited by 39
  9. 2021HTCInfoMax: A Global Model for Hierarchical Text Classification via Information Maximizationcited by 25
  10. 2018Neural Fine-Grained Entity Type Classification with Hierarchy-Aware Losscited by 20
  11. 2018A Tree-based Decoder for Neural Machine Translationcited by 18
  12. 2021Joint Learning of Hyperbolic Label Embeddings for Hierarchical Multi-label Classificationcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 3; 2024: 4; 2025: 1; 2026: 4.

13 papers.

Sort:

By area:

  1. 2023Hierarchical Verbalizer for Few-Shot Hierarchical Text Classificationcited by 11
  2. 2024Revisiting Hierarchical Text Classification: Inference and Metricscited by 7
  3. 2024HiGen: Hierarchy-Aware Sequence Generation for Hierarchical Text Classificationcited by 6
  4. 2023G2PTL: A Pre-trained Model for Delivery Address and its Applications in Logistics Systemcited by 4
  5. 2023Instances and Labels: Hierarchy-aware Joint Supervised Contrastive Learning for Hierarchical Multi-Label Text Classificationcited by 4
  6. 2024Analyzing Persuasive Strategies in Meme Texts: A Fusion of Language Models with Paraphrase Enrichmentcited by 2
  7. 2024Domain-Hierarchy Adaptation via Chain of Iterative Reasoning for Few-shot Hierarchical Text Classificationcited by 2
  8. 2026HCRE: LLM-based Hierarchical Classification for Cross-Document Relation Extraction with a Prediction-then-Verification Strategycited by 2
  9. 2022Are We Really Making Much Progress in Text Classification? A Comparative Reviewcited by 1
  10. 2025A Transformer-based Autoregressive Decoder Architecture for Hierarchical Text Classificationcited by 0
  11. 2026Taxon: Hierarchical Tax Code Prediction with Semantically Aligned LLM Expert Guidancecited by 0
  12. 2026FEAST: Retrieval-Augmented Multi-Hierarchical Food Classification for the FoodEx2 Systemcited by 0
1 more
  1. 2026SCHK-HTC: Sibling Contrastive Learning with Hierarchical Knowledge-Aware Prompt Tuning for Hierarchical Text Classificationcited by 0