STRUCTURAL ENCODING AND ATTENTION PARADIGMS FOR SEQUENCE MODELING

Systems and methods for providing a structure-aware sequence model that can interpret a document's text without first inferring the proper reading order of the document. In some examples, the model may use a graph convolutional network to generate contextualized "supertoken" embedding...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	LEE, Chen-Yu, FUJII, Yasuhisa, LI, Chun-Liang, SU, Guolong, PEROT, Vincent, AINSLIE, Joshua, WANG, Renshen, DOZAT, Timothy, PFISTER, Tomas, HUA, Nan
Format:	Patent
Sprache:	eng ; fre
Schlagworte:	CALCULATING COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!