Leveraging WordNet Paths for Neural Hypernym Prediction

Code

• github.com/scarletcho/hypernym-path-generation
  OfficialIn paperpytorch★ 3

Abstract

We formulate the problem of hypernym prediction as a sequence generation task, where the sequences are taxonomy paths in WordNet. Our experiments with encoder-decoder models show that training to generate taxonomy paths can improve the performance of direct hypernym prediction. As a simple but powerful model, the hypo2path model achieves state-of-the-art performance, outperforming the best benchmark by 4.11 points in hit-at-one (H@1).

Tasks

Reproductions