MUSS (BART+ACCESS Unsupervised)

Reported on 4 benchmarks across 1 task · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing4 results

Text SimplificationonTurkCorpus
FKGL· 2020-05-01
8.79
best: 9.33 (GPT-175B (6 SARI-selected examples, high/low))
SOTA
MUSS: Multilingual Unsupervised Sentence Simplification by Mining Paraphrases arXiv:2005.00352
Text SimplificationonASSET
FKGL· 2020-05-01
8.23
SOTA
MUSS: Multilingual Unsupervised Sentence Simplification by Mining Paraphrases arXiv:2005.00352
Text SimplificationonTurkCorpus
SARI (EASSE>=0.2.1)· 2020-05-01
40.85
best: 43.46 (GPT-175B (6 SARI-selected examples, high/low))
MUSS: Multilingual Unsupervised Sentence Simplification by Mining Paraphrases arXiv:2005.00352
Text SimplificationonASSET
SARI (EASSE>=0.2.1)· 2020-05-01
42.65
best: 47.94 (GPT-175B (15 SARI-selected examples, random ordering))
MUSS: Multilingual Unsupervised Sentence Simplification by Mining Paraphrases arXiv:2005.00352