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 1–10 of 33 papers

TitleStatusHype
OntoTune: Ontology-Driven Self-training for Aligning Large Language ModelsCode1
TaxoLLaMA: WordNet-based Model for Solving Multiple Lexical Semantic TasksCode1
Probing Pretrained Language Models with Hierarchy Properties—0
Modelling Commonsense Properties using Pre-Trained Bi-EncodersCode0
HyperBox: A Supervised Approach for Hypernym Discovery using Box Embeddings—0
CogALex 2.0: Impact of Data Quality on Lexical-Semantic Relation PredictionCode0
Analyzing BERT’s Knowledge of Hypernymy via Prompting—0
Hypernym Discovery via a Recurrent Mapping Model—0
Document Structure aware Relational Graph Convolutional Networks for Ontology Population—0
CogALex-VI Shared Task: Transrelation - A Robust Multilingual Language Model for Multilingual Relation IdentificationCode0
Show:102550
← PrevPage 1 of 4Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CRIMMAP19.78—Unverified
2vTEMAP10.6—Unverified
3NLP_HZMAP9.37—Unverified
4300-sparsansMAP8.95—Unverified
5MFHMAP8.77—Unverified
6SJTU BCMIMAP5.77—Unverified
7ApolloMAP2.68—Unverified
8balAPIncMAP1.36—Unverified