Search

Home > NLP Highlights > 24 - Improving Hypernymy Detection with an Integrated Path-based and Distributional Method
Podcast: NLP Highlights
Episode:

24 - Improving Hypernymy Detection with an Integrated Path-based and Distributional Method
Category: Science & Medicine
Duration: 00:16:33
Publish Date: 2017-06-27 16:10:04
Description: ACL 2016 outstanding paper, by Vered Shwartz, Yoav Goldberg and Ido Dagan. Waleed presents this paper, discussing hypernymy detection and the methods used in the paper. It's pretty similar to work in relation extraction and knowledge base completion, so we also talk a bit about connections to other methods we're familiar with. Encoding paths using an RNN like they do (and like Arvind Neelakantan did for KBC) improves recall substantially, at the cost of some precision, which makes intuitive sense. https://www.semanticscholar.org/paper/Improving-Hypernymy-Detection-with-an-Integrated-P-Shwartz-Goldberg/05d28e891fd70d123c46ceeb0cdfc0a2cb0d88db
Total Play: 0