COLING 2020main11 citations

Leveraging WordNet Paths for Neural Hypernym Prediction

Yejin Cho, Juan Diego Rodriguez, Yifan Gao, Katrin Erk

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).

BibTeX
@inproceedings{cho-etal-2020-leveraging,
    title = "Leveraging {W}ord{N}et Paths for Neural Hypernym Prediction",
    author = "Cho, Yejin  and
      Rodriguez, Juan Diego  and
      Gao, Yifan  and
      Erk, Katrin",
    editor = "Scott, Donia  and
      Bel, Nuria  and
      Zong, Chengqing",
    booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
    month = dec,
    year = "2020",
    address = "Barcelona, Spain (Online)",
    publisher = "International Committee on Computational Linguistics",
    url = "https://aclanthology.org/2020.coling-main.268/",
    doi = "10.18653/v1/2020.coling-main.268",
    pages = "3007--3018"
}