Pre-training Tasks for Embedding-based Large-scale Retrieval

We consider the large-scale query-document retrieval problem: given a query (e.g., a question), return the set of relevant documents (e.g., paragraphs containing the answer) from a large document corpus. This problem is often solved in two steps. The retrieval phase first reduces the solution space,...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Chang, Wei-Cheng, Yu, Felix X, Chang, Yin-Wen, Yang, Yiming, Kumar, Sanjiv
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Computation and Language Computer Science - Information Retrieval Computer Science - Learning Statistics - Machine Learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!