paper-with-me

Hypernym Discovery

3개 벤치마크 · 논문 33편 · 이 태스크의 논문 보기 →

Benchmarks

General

결과 16개

Medical domain

결과 16개

Music domain

결과 14개

Most implemented

Papers

OntoTune: Ontology-Driven Self-training for Aligning Large Language Models

2025-02-08 · Zhiqiang Liu, Chengtao Gan, Junjie Wang, Yichi Zhang 외

Existing domain-specific Large Language Models (LLMs) are typically developed by fine-tuning general-purposed LLMs with large-scale domain-specific corpora. However, training on large-scale corpora often fails to effecti…

Hypernym DiscoveryIn-Context Learning

TaxoLLaMA: WordNet-based Model for Solving Multiple Lexical Semantic Tasks

2024-03-14 · Viktor Moskvoretskii, Ekaterina Neminova, Alina Lobanova, Alexander Panchenko 외

In this paper, we explore the capabilities of LLMs in capturing lexical-semantic knowledge from WordNet on the example of the LLaMA-2-7b model and test it on multiple lexical semantic tasks. As the outcome of our experim…

Domain AdaptationFew-Shot LearningHypernym DiscoveryLexical Entailment+1

Probing Pretrained Language Models with Hierarchy Properties

2023-12-15 · Jesús Lovón-Melgarejo, Jose G. Moreno, Romaric Besançon, Olivier Ferret 외

Since Pretrained Language Models (PLMs) are the cornerstone of the most recent Information Retrieval (IR) models, the way they encode semantic knowledge is particularly important. However, little attention has been given…

Hypernym DiscoveryInformation RetrievalReading ComprehensionRetrieval

Modelling Commonsense Properties using Pre-Trained Bi-Encoders

2022-10-06 · COLING 2022 10 · Amit Gajbhiye, Luis Espinosa-Anke, Steven Schockaert

Grasping the commonsense properties of everyday concepts is an important prerequisite to language understanding. While contextualised language models are reportedly capable of predicting such commonsense properties with …

Hypernym Discovery

HyperBox: A Supervised Approach for Hypernym Discovery using Box Embeddings

2022-04-05 · LREC 2022 6 · Maulik Parmar, Dr. Apurva Narayan

Hypernymy plays a fundamental role in many AI tasks like taxonomy learning, ontology learning, etc. This has motivated the development of many automatic identification methods for extracting this relation, most of which …

Hypernym Discovery

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

2021-12-14 · NeurIPS Data-Centric AI Workshop 2021 12 · Christian Lang, Lennart Wachowiak, Barbara Heinisch, Dagmar Gromann

Predicting lexical-semantic relations between word pairs has successfully been accomplished by pre-trained neural language models. An XLM-RoBERTa-based approach, for instance, achieved the best performance differentiatin…

Hypernym DiscoveryRelationRelation ClassificationRelation Prediction

전체 33편 보기 →