Recent research on style transfer takes inspiration from unsupervised neural
machine translation (UNMT), learning from large amounts of non-parallel data by
exploiting cycle consistency loss, back-translation, and denoising
autoencoders. By contrast, the use of self-supervised NMT (SSNMT), which
leverages (near) parallel instances hidden in non-parallel data more
efficiently than UNMT, has not yet been explored for style transfer. In this
paper we present a novel Self-Supervised Style Transfer (3ST) model, which
augments SSNMT with UNMT methods in order to identify and efficiently exploit
supervisory signals in non-parallel social media posts. We compare 3ST with
state-of-the-art (SOTA) style transfer models across civil rephrasing,
formality and polarity tasks. We show that 3ST is able to balance the three
major objectives (fluency, content preservation, attribute transfer accuracy)
the best, outperforming SOTA models on averaged performance across their tested
tasks in automatic and human evaluation.

本篇论文提出一种新型自我监督的风格转换模型（3ST），根据社交媒体文章中的非并行实例，通过增强自我监督 NMT (SSNMT) 与 UNMT 方法，旨在有效地识别和利用监督信号，实现非并行数据的风格转换，表现良好。

利用社交媒体内容进行自监督风格转移

Exploiting Social Media Content for Self-Supervised Style Transfer

For most language combinations, parallel data is either scarce or simply
unavailable. To address this, unsupervised machine translation (UMT) exploits
large amounts of monolingual data by using synthetic data generation techniques
such as back-translation and noising, while self-supervised NMT (SSNMT)
identifies parallel sentences in smaller comparable data and trains on them. To
date, the inclusion of UMT data generation techniques in SSNMT has not been
investigated. We show that including UMT techniques into SSNMT significantly
outperforms SSNMT and UMT on all tested language pairs, with improvements of up
to +4.3 BLEU, +50.8 BLEU, +51.5 over SSNMT, statistical UMT and hybrid UMT,
respectively, on Afrikaans to English. We further show that the combination of
multilingual denoising autoencoding, SSNMT with backtranslation and bilingual
finetuning enables us to learn machine translation even for distant language
pairs for which only small amounts of monolingual data are available, e.g.
yielding BLEU scores of 11.6 (English to Swahili).

本文介绍了一种将无监督机器翻译和自监督 NMT 相结合的方法，该方法利用合成数据生成技术和 back-translation 的方法提高 SSNMT 的性能，特别是在缺乏语言对数据的情况下可以对距离较远的语言对进行翻译。