Local-to-Global Structure-Aware Transformer for Question Answering over Structured Knowledge

Question-answering tasks over structured knowledge (i.e., tables and graphs) require the ability to encode structural information. Traditional pre-trained language models trained on linear-chain natural language cannot be directly applied to encode tables and graphs. The existing methods adopt the p...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEICE Transactions on Information and Systems 2023/10/01, Vol.E106.D(10), pp.1705-1714
Hauptverfasser:	WANG, Yingyao, WANG, Han, DUAN, Chaoqun, ZHAO, Tiejun
Format:	Artikel
Sprache:	eng
Schlagworte:	Graphs Knowledge knowledge base question answering Knowledge bases (artificial intelligence) Knowledge representation Natural language processing pretrained transformer Questions Reasoning table fact verification
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!