DTaxa: An actor–critic for automatic taxonomy induction

Automatic taxonomy induction is a challenging task in the field of natural language understanding (NLU) and information retrieval (IR) because it requires machine learning and understanding the is-a relation (i.e. hypernym relation) between term pairs. Therefore, the deep taxa (DTaxa) based on the actor–critic algorithm framework is designed to deal with the aforementioned problems in this paper. The agent in the DTaxa regards the taxonomy induction process as the sequential decision steps so that the agent can take the operation of a term as an action via the policy network to jointly optimize hypernym detection and hypernym organization. Meanwhile, the DTaxa obtains a stable performance from the experiences buffered in the memory. In order to verify the effectiveness of the DTaxa for the automatic taxonomy induction, two experiments are performed on the all bottomed-out full subtrees extracted from WordNet 3.0 and the English environment and science taxonomies in the SemEval-2016 task 13, respectively. The proposed method outperforms these existing methods and achieves state-of-the-art among most metrics. [Display omitted] •The end-to-end DTaxa is proposed for automatic taxonomy induction.•The DTaxa based on actor–critic framework decreases large variance caused by REINFORCEMET algorithm.•The performance of the DTaxa is performed on two publicly available datasets.