A back-translation loop with three asymmetric initialization models (thresholded word alignment, reweighted bag-of-words denoising autoencoder, and word-presence moment matching) produces state-of-the-art unsupervised sentence summarization on Gigaword.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Unsupervised Text Summarization via Mixed Model Back-Translation
A back-translation loop with three asymmetric initialization models (thresholded word alignment, reweighted bag-of-words denoising autoencoder, and word-presence moment matching) produces state-of-the-art unsupervised sentence summarization on Gigaword.