ML Research Wiki / Benchmarks / Text Simplification / ASSET

ASSET

Text Simplification Benchmark

Performance Over Time

📊 Showing 11 results | 📏 Metric: BLEU

Top Performing Models

Rank Model Paper BLEU Date Code
1 GPT-175B (15 SARI-selected examples, random ordering) Metric-Based In-context Learning: A Case Study in Text Simplification 73.92 2023-07-27 📦 nlp-ku/metric-based-in-context-learning
2 MUSS (BART+ACCESS Supervised) MUSS: Multilingual Unsupervised Sentence Simplification by Mining Paraphrases 72.98 2020-05-01 📦 facebookresearch/muss
3 TST Text Simplification by Tagging 43.21 2021-03-08 📦 grammarly/gector
4 ACCESS Controllable Sentence Simplification 40.13 2019-10-07 📦 facebookresearch/access 📦 kvadityasrivatsa/gem_2021_simplification_task
5 DMASS-DCSS Integrating Transformer and Paraphrase Rules for Sentence Simplification 38.67 2018-10-26 📦 Sanqiang/text_simplification
6 Dress-LS Sentence Simplification with Deep Reinforcement Learning 36.59 2017-03-31 📦 XingxingZhang/dress
7 UNTS (Unsupervised) Unsupervised Neural Text Simplification 35.19 2018-10-18 📦 subramanyamdvss/UnsupNTS
8 MUSS (BART+ACCESS Unsupervised) MUSS: Multilingual Unsupervised Sentence Simplification by Mining Paraphrases 8.23 2020-05-01 📦 facebookresearch/muss
9 Control Prefixes (BART) Control Prefixes for Parameter-Efficient Text Generation 5.97 2021-10-15 📦 Yale-LILY/dart 📦 jordiclive/ControlPrefixes
10 T5 The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics 0.58 2021-02-02 -

All Papers (11)

Metric-Based In-context Learning: A Case Study in Text Simplification

2023
GPT-175B (15 SARI-selected examples, random ordering)
nlp-ku/metric-based-in-context-learning
facebookresearch/muss
grammarly/gector
facebookresearch/access kvadityasrivatsa/gem_2021_simplification_task
Sanqiang/text_simplification
XingxingZhang/dress
subramanyamdvss/UnsupNTS
facebookresearch/muss
Yale-LILY/dart jordiclive/ControlPrefixes