Taxonomy Completion via Triplet Matching Network

Authors

  • Jieyu Zhang University of Washington
  • Xiangchen Song University of Illinois at Urbana-Champaign
  • Ying Zeng ByteDance AI Lab
  • Jiaze Chen ByteDance AI Lab
  • Jiaming Shen University of Illinois at Urbana-Champaign
  • Yuning Mao University of Illinois at Urbana-Champaign
  • Lei Li ByteDance AI Lab

Keywords:

Web Ontologies -- Creation, Extraction, Evolution, Linked Open Data, Knowledge Graphs & KB Completio, Information Extraction

Abstract

Automatically constructing taxonomy finds many applications in e-commerce and web search. One critical challenge is as data and business scope grow in real applications, new concepts are emerging and needed to be added to the existing taxonomy. Previous approaches focus on the taxonomy expansion, i.e. finding an appropriate hypernym concept from the taxonomy for a new query concept. In this paper, we formulate a new task, “taxonomy completion”, by discovering both the hypernym and hyponym concepts for a query. We propose Triplet Matching Network (TMN), to find the appropriate pairs for a given query concept. TMN consists of one primal scorer and multiple auxiliary scorers. These auxiliary scorers capture various fine-grained signals (e.g., query to hypernym or query to hyponym semantics), and the primal scorer makes a holistic prediction on triplet based on the internal feature representations of all auxiliary scorers. Also, an innovative channel-wise gating mechanism that retains task-specific information in concept representations is introduced to further boost model performance. Experiments on four real-world large-scale datasets show that TMN achieves the best performance on both taxonomy completion task and the previous taxonomy expansion task, outperforming existing methods.

Downloads

Published

2021-05-18

How to Cite

Zhang, J., Song, X., Zeng, Y., Chen, J., Shen, J., Mao, Y., & Li, L. (2021). Taxonomy Completion via Triplet Matching Network. Proceedings of the AAAI Conference on Artificial Intelligence, 35(5), 4662-4670. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16596

Issue

Section

AAAI Technical Track on Data Mining and Knowledge Management