STEAM: Self-Supervised Taxonomy Expansion with Mini-Paths
arXiv:2006.10217 · doi:10.1145/3394486.3403145
Abstract
Taxonomies are important knowledge ontologies that underpin numerous applications on a daily basis, but many taxonomies used in practice suffer from the low coverage issue. We study the taxonomy expansion problem, which aims to expand existing taxonomies with new concept terms. We propose a self-supervised taxonomy expansion model named STEAM, which leverages natural supervision in the existing taxonomy for expansion. To generate natural self-supervision signals, STEAM samples mini-paths from the existing taxonomy, and formulates a node attachment prediction task between anchor mini-paths and query terms. To solve the node attachment task, it learns feature representations for query-anchor pairs from multiple views and performs multi-view co-training for prediction. Extensive experiments show that STEAM outperforms state-of-the-art methods for taxonomy expansion by 11.6\% in accuracy and 7.0\% in mean reciprocal rank on three public benchmarks. The implementation of STEAM can be found at \url{https://github.com/yueyu1030/STEAM}.
KDD 2020 Research Track Full Paper
References in corpus (2)
Cited by in corpus (9)
- SumGNN: Multi-typed Drug Interaction Prediction via Efficient Knowledge Graph Summarization
- Enhancing Taxonomy Completion with Concept Generation via Fusing Relational Representations
- TaxoEnrich: Self-Supervised Taxonomy Completion via Structure-Semantic Representations
- TaxoCom: Topic Taxonomy Completion with Hierarchical Discovery of Novel Topic Clusters
- Enquire One's Parent and Child Before Decision: Fully Exploit Hierarchical Structure for Self-Supervised Taxonomy Expansion
- Adaptive Multi-view Rule Discovery for Weakly-Supervised Compatible Products Prediction
- Who Should Go First? A Self-Supervised Concept Sorting Model for Improving Taxonomy Expansion
- Towards Visual Taxonomy Expansion
- Taxonomy Completion via Triplet Matching Network