Hybrid Strategies for Attribute Relation Learning from Candidates

Attribute relation learning is important, but has been few studied. This paper proposes hybrid strategies for attribute relation acquisition from candidate attributes. The composition of candidate attributes is firstly analyzed and subdivided into three types: non-attribute vocabularies, invalid attribute, and valid attribute. Secondly, the HowNet-based filtering strategy is presented which filters out the non-attribute vocabularies and invalid attributes from the candidates using the knowledge of “is-a” relations and attribute-host relations described by attribute sememe in HowNet. Thirdly, the pruning strategy based on domain concept tree is proposed to further perfect the associations between a concept and its candidate attributes. We define some pruning rules through which some redundant, unreliable, even wrong attributes can be discarded from candidates and some lost attributes can be recalled. Our results about attribute relation learning show the efficiency of our hybrid strategies.