{Caroline Barri{\`e}re Gabriel Bernier-Colborne}
Abstract
This report describes the system developed by the CRIM team for the hypernym discovery task at SemEval 2018. This system exploits a combination of supervised projection learning and unsupervised pattern-based hypernym discovery. It was ranked first on the 3 sub-tasks for which we submitted results.
Benchmarks
| Benchmark | Methodology | Metrics |
|---|---|---|
| hypernym-discovery-on-general | CRIM | MAP: 19.78 MRR: 36.10 P@5: 19.03 |
| hypernym-discovery-on-medical-domain | CRIM | MAP: 34.05 MRR: 54.64 P@5: 36.77 |
| hypernym-discovery-on-music-domain | CRIM | MAP: 40.97 MRR: 60.93 P@5: 41.31 |
Build AI with AI
From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.
AI Co-coding
Ready-to-use GPUs
Best Pricing
Hyper Newsletters
Subscribe to our latest updates
We will deliver the latest updates of the week to your inbox at nine o'clock every Monday morning
Powered by MailChimp