| Top Down Transformer (AdaPool) (464M) |
- ROUGE-1
- 50.95
- ROUGE-2
- 21.93
- ROUGE-L
- 45.61
|
Long Document Summarization with Top-down and Bottom-up Inference 2022-03-15 |
코드 1 |
| BART-LS |
- ROUGE-1
- 50.2
|
Adapting Pretrained Text-to-Text Models for Long Text Sequences 2022-09-21 |
코드 1 |
| Pegasus-X |
- ROUGE-1
- 50.0
- ROUGE-2
- 21.8
- ROUGE-L
- 44.6
|
Investigating Efficiently Extending Transformers for Long Input Summarization 2022-08-08 |
코드 1 · 코드 2 |
| ExtSum + oracle segmentation (extractive) |
- ROUGE-1
- 49.49
- ROUGE-2
- 21.04
- ROUGE-L
- 44.34
|
Document Summarization with Text Segmentation 2023-01-20 |
연결 없음 |
| FactorSum |
- ROUGE-1
- 49.32
- ROUGE-2
- 20.27
- ROUGE-L
- 44.76
|
Factorizing Content and Budget Decisions in Abstractive Summarization of Long Documents 2022-05-25 |
코드 1 |
| ExtSum + supervised segmentation (extractive) |
- ROUGE-1
- 49.11
- ROUGE-2
- 20.68
- ROUGE-L
- 44.01
|
Document Summarization with Text Segmentation 2023-01-20 |
연결 없음 |
| Lodoss-full-large (extractive) |
- ROUGE-1
- 48.45
- ROUGE-2
- 20.72
- ROUGE-L
- 42.55
|
Toward Unifying Text Segmentation and Long Document Summarization 2022-10-28 |
코드 1 |
| MemSum (extractive) |
- ROUGE-1
- 48.42
- ROUGE-2
- 20.30
- ROUGE-L
- 42.54
|
MemSum: Extractive Summarization of Long Documents Using Multi-Step Episodic Markov Decision Processes 2021-07-19 |
코드 1 |
| LongT5 |
- ROUGE-1
- 48.35
- ROUGE-2
- 21.92
- ROUGE-L
- 44.27
|
LongT5: Efficient Text-To-Text Transformer for Long Sequences 2021-12-15 |
코드 1 · 코드 2 · 코드 3 · 코드 4 |
| Lodoss-full-base (extractive) |
- ROUGE-1
- 48.20
- ROUGE-2
- 20.50
- ROUGE-L
- 42.28
|
Toward Unifying Text Segmentation and Long Document Summarization 2022-10-28 |
코드 1 |
| DeepPyramidion |
- ROUGE-1
- 47.15
- ROUGE-2
- 19.99
|
Sparsifying Transformer Models with Trainable Representation Pooling 2021-11-16 |
연결 없음 |
| Blockwise(baseline) |
- ROUGE-1
- 46.85
- ROUGE-2
- 19.39
|
Sparsifying Transformer Models with Trainable Representation Pooling 2021-11-16 |
연결 없음 |
| HAT-BART |
- ROUGE-1
- 46.74
- ROUGE-2
- 19.19
- ROUGE-L
- 42.2
|
Hierarchical Learning for Generation with Long Source Sequences 2021-04-15 |
연결 없음 |
| HiStruct+ |
- ROUGE-1
- 45.22
- ROUGE-2
- 17.67
- ROUGE-L
- 40.16
|
HiStruct+: Improving Extractive Text Summarization with Hierarchical Structure Information 2022-03-17 |
연결 없음 |
| DANCER PEGASUS |
- ROUGE-1
- 45.01
- ROUGE-2
- 17.6
- ROUGE-L
- 40.56
|
A Divide-and-Conquer Approach to the Summarization of Long Documents 2020-04-13 |
코드 1 |
| PEGASUS |
- ROUGE-1
- 44.67
|
PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization 2019-12-18 |
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8 · 코드 9 · 코드 10 · 코드 11 · 코드 12 · 코드 13 · 코드 14 · 코드 15 · 코드 16 · 코드 17 · 코드 18 · 코드 19 |
| ExtSum-LG+RdLoss |
- ROUGE-1
- 44.01
- ROUGE-2
- 17.79
- ROUGE-L
- 39.09
|
Systematically Exploring Redundancy Reduction in Summarizing Long Documents 2020-11-30 |
코드 1 |
| ExtSum-LG+MMR-Select+ |
- ROUGE-1
- 43.87
- ROUGE-2
- 17.5
- ROUGE-L
- 38.97
|
Systematically Exploring Redundancy Reduction in Summarizing Long Documents 2020-11-30 |
코드 1 |
| ExtSum-LG |
- ROUGE-1
- 43.58
- ROUGE-2
- 17.37
|
Extractive Summarization of Long Documents by Combining Global and Local Context 2019-09-17 |
코드 1 |
| SRformer-BART |
- ROUGE-1
- 42.99
|
Segmented Recurrent Transformer: An Efficient Sequence-to-Sequence Model 2023-05-24 |
코드 1 |
| DANCER RUM |
- ROUGE-1
- 42.7
- ROUGE-2
- 16.54
- ROUGE-L
- 38.44
|
A Divide-and-Conquer Approach to the Summarization of Long Documents 2020-04-13 |
코드 1 |
| TLM-I+E |
- ROUGE-1
- 42.43
|
On Extractive and Abstractive Neural Document Summarization with Transformer Language Models 2019-09-07 |
코드 1 |
| Sent-PTR |
- ROUGE-1
- 42.32
|
On Extractive and Abstractive Neural Document Summarization with Transformer Language Models 2019-09-07 |
코드 1 |
| DANCER LSTM |
- ROUGE-1
- 41.87
- ROUGE-2
- 15.92
- ROUGE-L
- 37.61
|
A Divide-and-Conquer Approach to the Summarization of Long Documents 2020-04-13 |
코드 1 |
| GenCompareSum |
- ROUGE-1
- 39.96
- ROUGE-2
- 15.15
- ROUGE-L
- 36.19
|
GenCompareSum: a hybrid unsupervised summarization method using salience 논문 날짜 미기재 |
코드 1 |
| Discourse |
- ROUGE-1
- 35.80
|
A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents 2018-04-16 |
코드 1 · 코드 2 · 코드 3 |
| Sent-CLF |
- ROUGE-1
- 34.01
|
On Extractive and Abstractive Neural Document Summarization with Transformer Language Models 2019-09-07 |
코드 1 |
| Pntr-Gen-Seq2Seq |
- ROUGE-1
- 32.06
|
Get To The Point: Summarization with Pointer-Generator Networks 2017-04-14 |
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8 · 코드 9 · 코드 10 · 코드 11 · 코드 12 · 코드 13 · 코드 14 · 코드 15 · 코드 16 · 코드 17 · 코드 18 · 코드 19 · 코드 20 · 코드 21 · 코드 22 · 코드 23 · 코드 24 · 코드 25 · 코드 26 · 코드 27 · 코드 28 · 코드 29 · 코드 30 · 코드 31 · 코드 32 · 코드 33 · 코드 34 · 코드 35 · 코드 36 · 코드 37 · 코드 38 · 코드 39 |