Enquire One's Parent and Child Before Decision: Fully Exploit Hierarchical Structure for Self-Supervised Taxonomy Expansion

Abstract

Taxonomy is a hierarchically structured knowledge graph that plays a crucial role in machine intelligence. The taxonomy expansion task aims to find a position for a new term in an existing taxonomy to capture the emerging knowledge in the world and keep the taxonomy dynamically updated. Previous taxonomy expansion solutions neglect valuable information brought by the hierarchical structure and evaluate the correctness of merely an added edge, which downgrade the problem to node-pair scoring or mini-path classification. In this paper, we propose the Hierarchy Expansion Framework (HEF), which fully exploits the hierarchical structure's properties to maximize the coherence of expanded taxonomy. HEF makes use of taxonomy's hierarchical structure in multiple aspects: i) HEF utilizes subtrees containing most relevant nodes as self-supervision data for a complete comparison of parental and sibling relations; ii) HEF adopts a coherence modeling module to evaluate the coherence of a taxonomy's subtree by integrating hypernymy relation detection and several tree-exclusive features; iii) HEF introduces the Fitting Score for position selection, which explicitly evaluates both path and level selections and takes full advantage of parental relations to interchange information for disambiguation and selfcorrection. Extensive experiments show that by better exploiting the hierarchical structure and optimizing taxonomy's coherence, HEF vastly surpasses the prior state-of-the-art on three benchmark datasets by an average improvement of 46.7% in accuracy and 32.3% in mean reciprocal rank.

GANTEE: Generative Adversarial Network for Taxonomy Enterance Evaluation

“…The second category focus on learning good representations for all concepts. Open source (Yu et al 2020), user-clicked-logs (Cheng et al 2022 and parent-child information (Wang et al 2021(Wang et al , 2022 are all used by the previous methods to learn a better representation for concepts. Besides, there exist many studies use PLMs during the representation learning stage (Cheng et al 2022;Wang et al 2022;Takeoka, Akimoto, and Oyamada 2021), however, these methods only use the PLMs as a external information provider to learn a better representation.…”

“…However, we argue that these methods (Yu et al 2020;Wang et al 2022;Cheng et al 2022;Shen et al 2020;Mao et al 2020;Wang et al 2021;Zhang et al 2021) have two drawbacks when being applied to real applications. First, these methods suffer from low effectiveness in real applications due to limited ability to represent the semantics of concepts.…”

Learning What You Need from What You Did: Product Taxonomy Expansion with User Behaviors Supervision

“…Song et al [22] design a concept sorting model to extract hyponymy relations and sort their insertion order by utilizing the relationship between the newly mined concepts. Wang et al [57] utilize the hierarchical information of the existing taxonomy by extracting tree-exclusive features in the taxonomy for better taxonomy coherence. One limitation of these approaches is that they mainly focus on the general-purpose taxonomies or utilize the general text corpora.…”