# TaxoEnrich: Self-Supervised Taxonomy Completion via Structure-Semantic Representations

arXiv: https://arxiv.org/abs/2202.04887 · HTML: https://mlsanity.com/paper/2202.04887/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 41 references that are in the map.
- First posted on arXiv 10 Feb 2022.

## Builds on (most cited first, 17 of 17)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [SciBERT: A Pretrained Language Model for Scientific Text](https://mlsanity.com/paper/1903.10676/) (2019)
- [Graph Convolutional Neural Networks for Web-Scale Recommender Systems](https://mlsanity.com/paper/1806.01973/) (2018)
- [Junction Tree Variational Autoencoder for Molecular Graph Generation](https://mlsanity.com/paper/1802.04364/) (2018)
- [TaxoGen: Unsupervised Topic Taxonomy Construction by Adaptive Term Embedding and Clustering](https://mlsanity.com/paper/1812.09551/) (2018)
- [TaxoExpan: Self-supervised Taxonomy Expansion with Position-Enhanced Graph Neural Network](https://mlsanity.com/paper/2001.09522/) (2020)
- [STEAM: Self-Supervised Taxonomy Expansion with Mini-Paths](https://mlsanity.com/paper/2006.10217/) (2020)
- [Hearst Patterns Revisited: Automatic Hypernym Detection from Large Text Corpora](https://mlsanity.com/paper/1806.03191/) (2018)
- [Taxonomy Completion via Triplet Matching Network](https://mlsanity.com/paper/2101.01896/) (2021)
- [CoRel: Seed-Guided Topical Taxonomy Construction by Concept Learning and Relation Transferring](https://mlsanity.com/paper/2010.06714/) (2020)
- [Enhancing Taxonomy Completion with Concept Generation via Fusing Relational Representations](https://mlsanity.com/paper/2106.02974/) (2021)
- [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)
- [Entity Set Search of Scientific Literature: An Unsupervised Ranking Approach](https://mlsanity.com/paper/1804.10877/) (2018)
- [Who Should Go First? A Self-Supervised Concept Sorting Model for Improving Taxonomy Expansion](https://mlsanity.com/paper/2104.03682/) (2021)
- [Taxonomy Induction using Hypernym Subsequences](https://mlsanity.com/paper/1704.07626/) (2017)

## Built on by (most cited first, 20 of 20)

- [YAGO 4.5: A Large and Clean Knowledge Base with a Rich Taxonomy](https://mlsanity.com/paper/2308.11884/) (2023)
- [OAG-Bench: A Human-Curated Benchmark for Academic Graph Mining](https://mlsanity.com/paper/2402.15810/) (2024)
- [TaxoLLaMA: WordNet-based Model for Solving Multiple Lexical Semantic Tasks](https://mlsanity.com/paper/2403.09207/) (2024)
- [A Unified Taxonomy-Guided Instruction Tuning Framework for Entity Set Expansion and Taxonomy Expansion](https://mlsanity.com/paper/2402.13405/) (2024)
- [Ontology Enrichment from Texts: A Biomedical Dataset for Concept Discovery and Placement](https://mlsanity.com/paper/2306.14704/) (2023)
- [generAItor: Tree-in-the-Loop Text Generation for Language Model Explainability and Adaptation](https://mlsanity.com/paper/2403.07627/) (2024)
- [Rank, Chunk and Expand: Lineage-Oriented Reasoning for Taxonomy Expansion](https://mlsanity.com/paper/2505.13282/) (2025)
- [FLAME: Self-Supervised Low-Resource Taxonomy Expansion using Large Language Models](https://mlsanity.com/paper/2402.13623/) (2024)
- [Self-supervised Topic Taxonomy Discovery in the Box Embedding Space](https://mlsanity.com/paper/2408.15050/) (2024)
- [OntoType: Ontology-Guided and Pre-Trained Language Model Assisted Fine-Grained Entity Typing](https://mlsanity.com/paper/2305.12307/) (2023)
- [LITE: LLM-Impelled efficient Taxonomy Evaluation](https://mlsanity.com/paper/2504.01369/) (2025)
- [TaxoBell: Gaussian Box Embeddings for Self-Supervised Taxonomy Expansion](https://mlsanity.com/paper/2601.09633/) (2026)
- [Insert or Attach: Taxonomy Completion via Box Embedding](https://mlsanity.com/paper/2305.11004/) (2023)
- [Polaris: Coupled Orbital Polar Embeddings for Hierarchical Concept Learning](https://mlsanity.com/paper/2605.00265/) (2026)
- [DNG: Taxonomy Expansion by Exploring the Intrinsic Directed Structure on Non-gaussian Space](https://mlsanity.com/paper/2302.11165/) (2023)
- [Towards Visual Taxonomy Expansion](https://mlsanity.com/paper/2309.06105/) (2023)
- [SciDef: Datasets and Tools for Automated Definition Extraction from Scientific Literature with LLMs](https://mlsanity.com/paper/2602.05413/) (2026)
- [COntExt: Towards Context-Aware Ontology Extension from Operational Metrics](https://mlsanity.com/paper/2607.29553/) (2026)
- [TaxCE : A Framework for Automated Taxonomy Construction and Evaluation at Scale](https://mlsanity.com/paper/2608.30614/) (2026)
- [Towards Automatic Evolution Tree Generation from Citation Graphs](https://mlsanity.com/paper/2609.09561/) (2026)

## Abstract (arXiv)

Taxonomies are fundamental to many real-world applications in various domains, serving as structural representations of knowledge. To deal with the increasing volume of new concepts needed to be organized as taxonomies, researchers turn to automatically completion of an existing taxonomy with new concepts. In this paper, we propose TaxoEnrich, a new taxonomy completion framework, which effectively leverages both semantic features and structural information in the existing taxonomy and offers a better representation of candidate position to boost the performance of taxonomy completion. Specifically, TaxoEnrich consists of four components: (1) taxonomy-contextualized embedding which incorporates both semantic meanings of concept and taxonomic relations based on powerful pretrained language models; (2) a taxonomy-aware sequential encoder which learns candidate position representations by encoding the structural information of taxonomy; (3) a query-aware sibling encoder which adaptively aggregates candidate siblings to augment candidate position representations based on their importance to the query-position matching; (4) a query-position matching model which extends existing work with our new candidate position representations. Extensive experiments on four large real-world datasets from different domains show that TaxoEnrich achieves the best performance among all evaluation metrics and outperforms previous state-of-the-art methods by a large margin.