# Enquire One's Parent and Child Before Decision: Fully Exploit Hierarchical Structure for Self-Supervised Taxonomy Expansion

arXiv: https://arxiv.org/abs/2101.11268 · HTML: https://mlsanity.com/paper/2101.11268/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 54 references that are in the map.
- First posted on arXiv 27 Jan 2021.

## Builds on (most cited first, 22 of 22)

- [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)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Self-Attention with Relative Position Representations](https://mlsanity.com/paper/1803.02155/) (2018)
- [Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks](https://mlsanity.com/paper/1503.00075/) (2015)
- [Code Prediction by Feeding Trees to Transformers](https://mlsanity.com/paper/2003.13848/) (2020)
- [TaxoGen: Unsupervised Topic Taxonomy Construction by Adaptive Term Embedding and Clustering](https://mlsanity.com/paper/1812.09551/) (2018)
- [Inferring Concept Hierarchies from Text Corpora via Hyperbolic Embeddings](https://mlsanity.com/paper/1902.00913/) (2019)
- [TaxoExpan: Self-supervised Taxonomy Expansion with Position-Enhanced Graph Neural Network](https://mlsanity.com/paper/2001.09522/) (2020)
- [Hierarchical Taxonomy-Aware and Attentional Graph Capsule RCNNs for Large-Scale Multi-Label Text Classification](https://mlsanity.com/paper/1906.04898/) (2019)
- [HiExpan: Task-Guided Taxonomy Construction by Hierarchical Tree Expansion](https://mlsanity.com/paper/1910.08194/) (2019)
- [STEAM: Self-Supervised Taxonomy Expansion with Mini-Paths](https://mlsanity.com/paper/2006.10217/) (2020)
- [TXtract: Taxonomy-Aware Knowledge Extraction for Thousands of Product Categories](https://mlsanity.com/paper/2004.13852/) (2020)
- [Improving Hypernymy Detection with an Integrated Path-based and Distributional Method](https://mlsanity.com/paper/1603.06076/) (2016)
- [Hearst Patterns Revisited: Automatic Hypernym Detection from Large Text Corpora](https://mlsanity.com/paper/1806.03191/) (2018)
- [AliCoCo: Alibaba E-commerce Cognitive Concept Net](https://mlsanity.com/paper/2003.13230/) (2020)
- [End-to-End Reinforcement Learning for Automatic Taxonomy Induction](https://mlsanity.com/paper/1805.04044/) (2018)
- [MetaPAD: Meta Pattern Discovery from Massive Text Corpora](https://mlsanity.com/paper/1703.04213/) (2017)
- [A User-Centered Concept Mining System for Query and Document Understanding at Tencent](https://mlsanity.com/paper/1905.08487/) (2019)
- [GIANT: Scalable Creation of a Web-scale Ontology](https://mlsanity.com/paper/2004.02118/) (2020)
- [Taxonomy Induction using Hypernym Subsequences](https://mlsanity.com/paper/1704.07626/) (2017)
- [Term Definitions Help Hypernymy Detection](https://mlsanity.com/paper/1806.04532/) (2018)

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

- [Enhancing Taxonomy Completion with Concept Generation via Fusing Relational Representations](https://mlsanity.com/paper/2106.02974/) (2021)
- [HyperExpan: Taxonomy Expansion with Hyperbolic Representation Learning](https://mlsanity.com/paper/2109.10500/) (2021)
- [A Review on Knowledge Graphs for Healthcare: Resources, Applications, and Promises](https://mlsanity.com/paper/2306.04802/) (2023)
- [CodeTaxo: Enhancing Taxonomy Expansion with Limited Examples via Code Language Prompts](https://mlsanity.com/paper/2408.09070/) (2024)
- [A Unified Taxonomy-Guided Instruction Tuning Framework for Entity Set Expansion and Taxonomy Expansion](https://mlsanity.com/paper/2402.13405/) (2024)
- [Rank, Chunk and Expand: Lineage-Oriented Reasoning for Taxonomy Expansion](https://mlsanity.com/paper/2505.13282/) (2025)
- [Learning What You Need from What You Did: Product Taxonomy Expansion with User Behaviors Supervision](https://mlsanity.com/paper/2203.14921/) (2022)
- [FLAME: Self-Supervised Low-Resource Taxonomy Expansion using Large Language Models](https://mlsanity.com/paper/2402.13623/) (2024)
- [Expanding Knowledge Graphs with Humans in the Loop](https://mlsanity.com/paper/2212.05189/) (2022)
- [TaxoBell: Gaussian Box Embeddings for Self-Supervised Taxonomy Expansion](https://mlsanity.com/paper/2601.09633/) (2026)
- [GANTEE: Generative Adversatial Network for Taxonomy Entering Evaluation](https://mlsanity.com/paper/2303.14480/) (2023)
- [DNG: Taxonomy Expansion by Exploring the Intrinsic Directed Structure on Non-gaussian Space](https://mlsanity.com/paper/2302.11165/) (2023)
- [SPARROW: Scalable Taxonomy Induction via Structure-Preserving Partitioning and Constraint-Guided Merging](https://mlsanity.com/paper/2609.07307/) (2026)

## Abstract (arXiv)

Taxonomy is a hierarchically structured knowledge graph that plays a crucial role in machine intelligence. The taxonomy expansion task aims to find a position for a new term in an existing taxonomy to capture the emerging knowledge in the world and keep the taxonomy dynamically updated. Previous taxonomy expansion solutions neglect valuable information brought by the hierarchical structure and evaluate the correctness of merely an added edge, which downgrade the problem to node-pair scoring or mini-path classification. In this paper, we propose the Hierarchy Expansion Framework (HEF), which fully exploits the hierarchical structure's properties to maximize the coherence of expanded taxonomy. HEF makes use of taxonomy's hierarchical structure in multiple aspects: i) HEF utilizes subtrees containing most relevant nodes as self-supervision data for a complete comparison of parental and sibling relations; ii) HEF adopts a coherence modeling module to evaluate the coherence of a taxonomy's subtree by integrating hypernymy relation detection and several tree-exclusive features; iii) HEF introduces the Fitting Score for position selection, which explicitly evaluates both path and level selections and takes full advantage of parental relations to interchange information for disambiguation and self-correction. Extensive experiments show that by better exploiting the hierarchical structure and optimizing taxonomy's coherence, HEF vastly surpasses the prior state-of-the-art on three benchmark datasets by an average improvement of 46.7% in accuracy and 32.3% in mean reciprocal rank.