Towards Interpreting BERT for Reading Comprehension Based QA

BERT and its variants have achieved state-of-the-art performance in various NLP tasks. Since then, various works have been proposed to analyze the linguistic information being captured in BERT. However, the current works do not provide an insight into how BERT is able to achieve near human-level per...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2020-10
Hauptverfasser:	Ramnath, Sahana, Nema, Preksha, Sahni, Deep, Khapra, Mitesh M
Format:	Artikel
Sprache:	eng
Schlagworte:	Functionally gradient materials Human performance Questions Reading comprehension
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!