[Novel] Language-independent Taxonomy Derivation from Wikipedia via Multi-task Adversarial Learning

Shulin Cao, Zijun Yao, Lei Hou, Juanzi Li

TL;DR: Language-independent Taxonomy Derivation from Wikipedia via Multi-task Adversarial Learning

Abstract: Many recent efforts explore the task of Taxonomy Derivation from Wikipedia Category Network (TDWCN), which induces rich hypernymy relations between instances and classes from Wikipedia to integrate hierarchical information into knowledge graphs. However, current methods rely heavily on language-dependent information including heuristic rules, human annotations and inter-language links, which limit their applications. In this paper, we propose a language-independent model for TDWCN. Specifically, we design an adversarial learning approach to distill hypernymy relations from noisy raw Wikipedia, avoiding any language dependencies. Besides, we incorporate multi-task learning to explore the correlation among instanceOf, subClassOf, and the relations of instances. In addition, we contribute an English evaluation dataset ENT5k with about 6000 categories. Experimental results on 4 different languages demonstrate that our model can be applied generally to any language and achieve better or comparable performance compared with previous language-dependent models.

Submission Number: 11