HyperAIHyperAI
AccueilActualitésArticles de recherche récentsTutorielsEnsembles de donnéesWikiSOTAModèles LLMClassement GPUÉvénements
Recherche
À propos
HyperAIHyperAI

Question Answering On Cnn Daily Mail

Métriques

CNN
Daily Mail

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle
CNN
Daily Mail
Paper TitleRepository
Impatient Reader63.868.0Teaching Machines to Read and Comprehend
Classifier67.968.3A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task
GA Reader77.980.9Gated-Attention Readers for Text Comprehension
AoA Reader74.4-Attention-over-Attention Neural Networks for Reading Comprehension
Attentive + relabling + ensemble77.679.2A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task
AIA76.1-Iterative Alternating Neural Attention for Machine Reading
AS Reader (ensemble model)75.477.7Text Understanding with the Attention Sum Reader Network
AS Reader (single model) 69.573.9Text Understanding with the Attention Sum Reader Network
EpiReader74-Natural Language Comprehension with the EpiReader-
GA+MAGE (32)78.6-Linguistic Knowledge as Memory for Recurrent Neural Networks-
Attentive Reader6369Teaching Machines to Read and Comprehend
AttentiveReader + bilinear attention72.475.8A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task
MemNNs (ensemble)69.4-Teaching Machines to Read and Comprehend
ReasoNet74.776.6ReasoNet: Learning to Stop Reading in Machine Comprehension-
BiDAF76.979.6Bidirectional Attention Flow for Machine Comprehension
Dynamic Entity Repres. + w2v 72.9---
0 of 16 row(s) selected.