HyperAI超神経

プラットフォーム

Extractive Document Summarization On Cnn

評価指標

ROUGE-1

ROUGE-2

ROUGE-L

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

				Paper Title
HAHSum	44.68	21.30	40.75	Neural Extractive Summarization with Hierarchical Attentive Heterogeneous Graph Network
MatchSum	44.41	20.86	40.55	Extractive Summarization as Text Matching
A2Summ	44.11	20.31	35.92	Align and Attend: Multimodal Summarization with Dual Contrastive Losses
NeRoBERTa	43.86	20.64	40.20	Considering Nested Tree Structure in Sentence Extractive Summarization with Pre-trained Transformer
BERT-ext + RL	42.76	19.87	39.11	Summary Level Training of Sentence Rewriting for Abstractive Summarization
PNBERT	42.69	19.60	38.85	Searching for Effective Neural Extractive Summarization: What Works and What's Next
HIBERT	42.37	19.95	38.83	HIBERT: Document Level Pre-training of Hierarchical Bidirectional Transformers for Document Summarization
HER	42.3	18.9	37.9	Reading Like HER: Human Reading Inspired Extractive Summarization
NeuSUM	41.59	19.01	37.98	Neural Document Summarization by Jointly Learning to Score and Select Sentences
BanditSum	41.5	18.7	37.6	BanditSum: Extractive Summarization as a Contextual Bandit
Latent	41.05	18.77	37.54	Neural Latent Extractive Document Summarization
Lead-3 baseline	40.34	17.70	36.57	Get To The Point: Summarization with Pointer-Generator Networks
REFRESH	40.0	18.2	36.6	Ranking Sentences for Extractive Summarization with Reinforcement Learning
ITS	30.80	12.6	-	Iterative Document Representation Learning Towards Summarization with Polishing

0 of 14 row(s) selected.

Extractive Document Summarization On Cnn | SOTA | HyperAI超神経