Find Parent then Label Children: A Two-stage Taxonomy Completion Method with Pre-trained Language Model
This addresses the need for dynamic taxonomy updates in knowledge systems, offering a more flexible approach than prior methods that only add leaf nodes.
The paper tackles the problem of updating taxonomies by inserting new concepts into non-leaf nodes, not just leaves, using a two-stage method called ATTEMPT that leverages pre-trained language models for hypernym/hyponym recognition. It achieves state-of-the-art performance on two public datasets across six domains.
Taxonomies, which organize domain concepts into hierarchical structures, are crucial for building knowledge systems and downstream applications. As domain knowledge evolves, taxonomies need to be continuously updated to include new concepts. Previous approaches have mainly focused on adding concepts to the leaf nodes of the existing hierarchical tree, which does not fully utilize the taxonomy's knowledge and is unable to update the original taxonomy structure (usually involving non-leaf nodes). In this paper, we propose a two-stage method called ATTEMPT for taxonomy completion. Our method inserts new concepts into the correct position by finding a parent node and labeling child nodes. Specifically, by combining local nodes with prompts to generate natural sentences, we take advantage of pre-trained language models for hypernym/hyponymy recognition. Experimental results on two public datasets (including six domains) show that ATTEMPT performs best on both taxonomy completion and extension tasks, surpassing existing methods.