Pixel Sentence Representation Learning

Pretrained language models are long known to be subpar in capturing sentence and document-level semantics. Though heavily investigated, transferring perturbation-based methods from unsupervised visual representation learning to NLP remains an unsolved problem. This is largely due to the discreteness...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-02
Hauptverfasser:	Xiao, Chenghao, Huang, Zhuoxu, Chen, Danlu, Hudson, G Thomas, Li, Yizhi, Duan, Haoran, Lin, Chenghua, Fu, Jie, Han, Jungong, Noura Al Moubayed
Format:	Artikel
Sprache:	eng
Schlagworte:	Documents Iterative methods Learning Natural language processing Perturbation methods Pixels Representations Semantics Sentences Subword units Training
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!