SOTAVerified

Hypernym Discovery

Given a corpus and a target term (hyponym), the task of hypernym discovery consists of extracting a set of its most appropriate hypernyms from the corpus. For example, for the input word “dog”, some valid hypernyms would be “canine”, “mammal” or “animal”.

Papers

Showing 2130 of 33 papers

TitleStatusHype
SemEval-2018 Task 9: Hypernym Discovery0
ADAPT at SemEval-2018 Task 9: Skip-Gram Word Embeddings for Unsupervised Hypernym Discovery in Specialised Corpora0
SJTU-NLP at SemEval-2018 Task 9: Neural Hypernym Discovery with Term Embeddings0
UMDuluth-CS8761 at SemEval-2018 Task 9: Hypernym Discovery using Hearst Patterns, Co-occurrence frequencies and Word Embeddings0
Tel(s)-Telle(s)-Signs: Highly Accurate Automatic Crosslingual Hypernym Discovery0
Hyperbolic Entailment Cones for Learning Hierarchical EmbeddingsCode1
Distributional Inclusion Vector Embedding for Unsupervised Hypernymy Detection0
BabelDomains: Large-Scale Domain Labeling of Lexical Resources0
Hypernyms under Siege: Linguistically-motivated Artillery for Hypernymy DetectionCode0
Supervised Distributional Hypernym Discovery via Domain Adaptation0
Show:102550
← PrevPage 3 of 4Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CRIMMAP19.78Unverified
2vTEMAP10.6Unverified
3NLP_HZMAP9.37Unverified
4300-sparsansMAP8.95Unverified
5MFHMAP8.77Unverified
6SJTU BCMIMAP5.77Unverified
7ApolloMAP2.68Unverified
8balAPIncMAP1.36Unverified
#ModelMetricClaimedVerifiedStatus
1CRIMMAP34.05Unverified
2MFHMAP28.93Unverified
3300-sparsansMAP20.75Unverified
4vTEMAP18.84Unverified
5EXPRMAP13.77Unverified
6SJTU BCMIMAP11.69Unverified
7ADAPTMAP8.13Unverified
8balAPIncMAP0.91Unverified
#ModelMetricClaimedVerifiedStatus
1CRIMMAP40.97Unverified
2MFHMAP33.32Unverified
3300-sparsansMAP29.54Unverified
4vTEMAP12.99Unverified
5SJTU BCMIMAP4.71Unverified
6ADAPTMAP2.63Unverified
7balAPIncMAP1.95Unverified