Low-resource Taxonomy Enrichment with Pretrained Language Models
Kunihiro Takeoka, Kosuke Akimoto, Masafumi Oyamada
2021Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing22 citationsDOIOpen Access PDF
Abstract
Taxonomies are symbolic representations of hierarchical relationships between terms or entities. While taxonomies are useful in broad applications, manually updating or maintaining them is labor-intensive and difficult to scale in practice. Conventional supervised methods for this enrichment task fail to find optimal parents of new terms in low-resource settings where only small taxonomies are available because of overfitting to hierarchical relationships in the taxonomies.
Topics & Concepts
Computer scienceLeverage (statistics)OverfittingArtificial intelligenceClassifier (UML)Taxonomy (biology)Machine learningTask (project management)Economic shortageNatural language processingInformation retrievalBiologyArtificial neural networkPhilosophyGovernment (linguistics)LinguisticsEconomicsManagementBotanyTopic ModelingNatural Language Processing TechniquesText and Document Classification Technologies