MoCoUTRL: a momentum contrastive framework for unsupervised text representation learning

This paper presents MoCoUTRL: a Momentum Contrastive Framework for Unsupervised Text Representation Learning. This model improves two aspects of recently popular contrastive learning algorithms in natural language processing (NLP). Firstly, MoCoUTRL employs multi-granularity semantic contrastive lea...

Descrizione completa

Dettagli Bibliografici

Autori principali:	Ao Zou, Wenning Hao, Dawei Jin, Gang Chen, Feiyan Sun
Natura:	Artigo
Lingua:	Inglês
Pubblicazione:	Taylor & Francis Group 2023-12-01
Serie:	Connection Science
Soggetti:	natural language processing text representation learning momentum contrast alignment uniformity
Accesso online:	http://dx.doi.org/10.1080/09540091.2023.2221406
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!