Litcius/Paper detail

Relational World Knowledge Representation in Contextual Language Models: A Review

Tara Safavi, Danai Koutra

2021Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing31 citationsDOIOpen Access PDF

Abstract

Relational knowledge bases (KBs) are commonly used to represent world knowledge in machines. However, while advantageous for their high degree of precision and interpretability, KBs are usually organized according to manually-defined schemas, which limit their expressiveness and require significant human efforts to engineer and maintain. In this review, we take a natural language processing perspective to these limitations, examining how they may be addressed in part by training deep contextual language models (LMs) to internalize and express relational knowledge in more flexible forms. We propose to organize knowledge representation strategies in LMs by the level of KB supervision provided, from no KB supervision at all to entity-and relation-level supervision. Our contributions are threefold:

Topics & Concepts

InterpretabilityComputer scienceKnowledge representation and reasoningTaxonomy (biology)Domain knowledgeRepresentation (politics)Artificial intelligenceRelation (database)Knowledge managementNatural language processingHuman–computer interactionData miningBotanyPoliticsBiologyLawPolitical scienceTopic ModelingNatural Language Processing TechniquesData Quality and Management