HyperAIHyperAI

Command Palette

Search for a command to run...

3 months ago

CRIM at SemEval-2018 Task 9: A Hybrid Approach to Hypernym Discovery

{Caroline Barri{\`e}re Gabriel Bernier-Colborne}

CRIM at SemEval-2018 Task 9: A Hybrid Approach to Hypernym Discovery

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

BenchmarkMethodologyMetrics
hypernym-discovery-on-generalCRIM
MAP: 19.78
MRR: 36.10
P@5: 19.03
hypernym-discovery-on-medical-domainCRIM
MAP: 34.05
MRR: 54.64
P@5: 36.77
hypernym-discovery-on-music-domainCRIM
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
Get Started

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
CRIM at SemEval-2018 Task 9: A Hybrid Approach to Hypernym Discovery | Papers | HyperAI