Text Summarization On Duc 2004 Task 1

Metrics

ROUGE-1

ROUGE-2

ROUGE-L

Results

Performance results of various models on this benchmark

				Paper Title
Transformer LM	-	17.74	-	Sample Efficient Text Summarization Using a Single Pre-Trained Transformer
Transformer+LRPE+PE+Re-ranking+Ensemble	32.85	11.78	28.52	Positional Encoding to Control Output Sequence Length
Transformer+LRPE+PE+ALONE+Re-ranking	32.57	11.63	28.24	All Word Embeddings from One Embedding
Transformer+WDrop	33.06	11.45	28.51	Rethinking Perturbations in Encoder-Decoders for Fast Training
Reinforced-Topic-ConvS2S	31.15	10.85	27.68	A Reinforced Topic-Aware Convolutional Sequence-to-Sequence Model for Abstractive Text Summarization
DRGD	31.79	10.75	27.48	Deep Recurrent Generative Decoder for Abstractive Text Summarization
EndDec+WFE	32.28	10.54	27.8	Cutting-off Redundant Repeating Generations for Neural Abstractive Summarization
Seq2seq + selective + MTL + ERAM	29.33	10.24	25.24	Ensure the Correctness of the Summary: Incorporate Entailment Knowledge into Abstractive Sentence Summarization
SEASS	29.21	9.56	25.51	Selective Encoding for Abstractive Sentence Summarization
words-lvt5k-1sent	28.61	9.42	25.24	Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond
Abs+	28.18	8.49	23.81	A Neural Attention Model for Abstractive Sentence Summarization
RAS-Elman	28.97	8.26	24.06	-
ABS	-	-	22.05	A Neural Attention Model for Abstractive Sentence Summarization

0 of 13 row(s) selected.

Text Summarization On Duc 2004 Task 1 | SOTA | HyperAI