MétaCan
Menu
Back to cohort
Record W3159836094 · doi:10.1145/3412841.3441959

Taxonomy extraction using knowledge graph embeddings and hierarchical clustering

2021· article· en· W3159836094 on OpenAlexaff
Félix Martel, Amal Zouaq

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicSemantic Web and Ontologies
Canadian institutionsPolytechnique Montréal
Fundersnot available
KeywordsComputer scienceAxiomCluster analysisKnowledge graphTaxonomy (biology)Semantic WebInformation retrievalGraphKnowledge extractionEntity linkingHierarchical clusteringInformation extractionArtificial intelligenceData miningTheoretical computer scienceNatural language processingKnowledge baseMathematics

Abstract

fetched live from OpenAlex

While high-quality taxonomies are essential to the Semantic Web, building them for large knowledge graphs is an expensive process. Likewise, creating taxonomies that accurately reflect the content of dynamic knowledge graphs is another challenge. In this paper, we propose a method to automatically extract a taxonomy from knowledge graph embeddings, and evaluate it on DBpedia. Our approach produces a taxonomy by leveraging the type information contained in the graph and the tree-like structure of an unsupervised hierarchical clustering performed over entity embeddings. We then extend our method with an axiom induction mechanism which allows us to identify new classes from the data and describe them with logical axioms, thus leading to expressive taxonomy extraction.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.009
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.009
Threshold uncertainty score0.014

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.009
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.002
Bibliometrics0.0090.007
Science and technology studies0.0010.001
Scholarly communication0.0020.005
Open science0.0010.002
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0020.002

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.061
GPT teacher head0.305
Teacher spread0.244 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations12
Published2021
Admission routes1
Has abstractyes

Explore more

Same topicSemantic Web and OntologiesFrench-language works237,207