Hypernym Discovery

7 papers with code • 3 benchmarks • 1 datasets

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”.

Most implemented papers

Hyperbolic Entailment Cones for Learning Hierarchical Embeddings

dalab/hyperbolic_cones ICML 2018

Learning graph representations via low-dimensional embeddings that preserve relevant network properties is an important class of problems in machine learning.

Hypernyms under Siege: Linguistically-motivated Artillery for Hypernymy Detection

vered1986/UnsupervisedHypernymy EACL 2017

The fundamental role of hypernymy in NLP has motivated the development of many methods for the automatic identification of this relation, most of which rely on word distribution.

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

gbcolborne/hypernym_discovery SEMEVAL 2018

This report describes the system developed by the CRIM team for the hypernym discovery task at SemEval 2018.

Meemi: A Simple Method for Post-processing and Integrating Cross-lingual Word Embeddings

yeraidm/meemi 16 Oct 2019

While monolingual word embeddings encode information about words in the context of a particular language, cross-lingual embeddings define a multilingual space where word embeddings from two or more languages are integrated together.

CogALex-VI Shared Task: Transrelation - A Robust Multilingual Language Model for Multilingual Relation Identification

Text2TCS/Transrelation 12 Dec 2020

We describe our submission to the CogALex-VI shared task on the identification of multilingual paradigmatic relations building on XLM-RoBERTa (XLM-R), a robustly optimized and multilingual BERT model.

CogALex 2.0: Impact of Data Quality on Lexical-Semantic Relation Prediction

Text2TCS/CogALex-2.0 NeurIPS Data-Centric AI Workshop 2021

Predicting lexical-semantic relations between word pairs has successfully been accomplished by pre-trained neural language models.

Modelling Commonsense Properties using Pre-Trained Bi-Encoders

amitgajbhiye/biencoder_concept_property COLING 2022

Grasping the commonsense properties of everyday concepts is an important prerequisite to language understanding.