Beat the AI: Investigating Adversarial Human Annotation for Reading Comprehension

Innovations in annotation methodology have been a catalyst for Reading Comprehension (RC) datasets and models. One recent trend to challenge current RC models is to involve a model in the annotation process: Humans create questions adversarially, such that the model fails to answer them correctly. I...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Transactions of the Association for Computational Linguistics 2020-01, Vol.8, p.662-678
Hauptverfasser:	Bartolo, Max, Roberts, Alastair, Welbl, Johannes, Riedel, Sebastian, Stenetorp, Pontus
Format:	Artikel
Sprache:	eng
Schlagworte:	Annotations Datasets Generalization Performance degradation Questions Reading comprehension
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!