mlsanityData to 7 Oct 2026

Ontology Completion with Natural Language Inference and Concept Embeddings: An Analysis

arXiv 2403.17216 ↗First posted 25 Mar 2024cs.CLcited by 4

Not on the map. Why?

Abstract (arXiv)

We consider the problem of finding plausible knowledge that is missing from a given ontology, as a generalisation of the well-studied taxonomy expansion task. One line of work treats this task as a Natural Language Inference (NLI) problem, thus relying on the knowledge captured by language models to identify the missing knowledge. Another line of work uses concept embeddings to identify what different concepts have in common, taking inspiration from cognitive models for category based induction. These two approaches are intuitively complementary, but their effectiveness has not yet been compared. In this paper, we introduce a benchmark for evaluating ontology completion methods and thoroughly analyse the strengths and weaknesses of both approaches. We find that both approaches are indeed complementary, with hybrid strategies achieving the best overall results. We also find that the task is highly challenging for Large Language Models, even after fine-tuning.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 27 of its 56 references that are in the map. First posted on arXiv 25 Mar 2024.

Builds on

27 of 56 references.

References · 27

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  4. 2017Graph Attention Networkscited by 8,854
  5. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  6. 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,065
  7. 2017Poincar'e Embeddings for Learning Hierarchical Representationscited by 674
  8. 2018Hyperbolic Entailment Cones for Learning Hierarchical Embeddingscited by 160
  9. 2021Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoderscited by 88
  10. 2018Probabilistic Embedding of Knowledge Graphs with Box Lattice Measurescited by 64
  11. 2019Inferring Concept Hierarchies from Text Corpora via Hyperbolic Embeddingscited by 49
  12. 2019EL Embeddings: Geometric construction of models for the Description Logic EL ++cited by 48
15 more
  1. 2022Contextual Semantic Embeddings for Ontology Subsumption Predictioncited by 31
  2. 2023Exploring Large Language Models for Ontology Alignmentcited by 26
  3. 2018OPA2Vec: combining formal and informal content of biomedical ontologies to improve similarity-based predictioncited by 25
  4. 2023Language Model Analysis for Ontology Subsumption Inferencecited by 25
  5. 2020Constructing Taxonomies from Pretrained Language Modelscited by 21
  6. 2023DeepOnto: A Python Package for Ontology Engineering with Deep Learningcited by 20
  7. 2018Onto2Vec: joint vector-based representation of biological entities and their ontology-based annotationscited by 18
  8. 2021MirrorWiC: On Eliciting Word-in-Context Representations from Pretrained Language Modelscited by 18
  9. 2018Efficient Concept Induction for Description Logicscited by 17
  10. 2022Description Logic EL++ Embeddings with Intersectional Closurecited by 15
  11. 2021Learning Description Logic Ontologies. Five Approaches. Where Do They Stand?cited by 12
  12. 2022Modelling Commonsense Properties using Pre-Trained Bi-Encoderscited by 9
  13. 2023Distilling Semantic Concept Embeddings from Contrastively Fine-Tuned Language Modelscited by 8
  14. 2015Representing Meaning with a Combination of Logical and Distributional Modelscited by 6
  15. 2020Modelling General Properties of Nouns by Selectively Averaging Contextualised Embeddingscited by 6

Built on by

Cited by year

Citing papers per year: 2024: 2; 2025: 2.

4 papers.

  1. 2025OntoURL: A Benchmark for Evaluating Large Language Models on Symbolic Ontological Understanding, Reasoning and Learningcited by 6
  2. 2025Language Models as Ontology Encoderscited by 4
  3. 2024Enhancing Geometric Ontology Embeddings for EL++ with Negative Sampling and Deductive Closure Filteringcited by 1
  4. 2024Text Classification using Graph Convolutional Networks: A Comprehensive Surveycited by 1