Unsupervised Context Aware Sentence Representation Pretraining for Multi-lingual Dense Retrieval

Recent research demonstrates the effectiveness of using pretrained language models (PLM) to improve dense retrieval and multilingual dense retrieval. In this work, we present a simple but effective monolingual pretraining task called contrastive context prediction~(CCP) to learn sentence representat...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Wu, Ning, Liang, Yaobo, Ren, Houxing, Shou, Linjun, Duan, Nan, Gong, Ming, Jiang, Daxin
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Information Retrieval
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!