Predicting Semantic Relations using Global Graph Properties

EMNLP 2018 Yuval PinterJacob Eisenstein

Semantic graphs, such as WordNet, are resources which curate natural language on two distinguishable layers. On the local level, individual relations between synsets (semantic building blocks) such as hypernymy and meronymy enhance our understanding of the words used to express their meanings... (read more)

PDF Abstract

Evaluation Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK COMPARE
Link Prediction WN18RR M3GM MRR 0.4983 # 1
Link Prediction WN18RR M3GM [email protected] 0.5902 # 1
Link Prediction WN18RR M3GM [email protected] 0.4537 # 3