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 110 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 Properties0
Modelling Commonsense Properties using Pre-Trained Bi-EncodersCode0
HyperBox: A Supervised Approach for Hypernym Discovery using Box Embeddings0
CogALex 2.0: Impact of Data Quality on Lexical-Semantic Relation PredictionCode0
Analyzing BERT’s Knowledge of Hypernymy via Prompting0
Hypernym Discovery via a Recurrent Mapping Model0
Document Structure aware Relational Graph Convolutional Networks for Ontology Population0
CogALex-VI Shared Task: Transrelation - A Robust Multilingual Language Model for Multilingual Relation IdentificationCode0
Show:102550
← PrevPage 1 of 4Next →

Benchmark Results

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