A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/2106.10608v1.pdf">the original URL</a>. The file type is <code>application/pdf</code>.
Multi-Pair Text Style Transfer on Unbalanced Data
[article]
<span title="2021-06-20">2021</span>
<i >
arXiv
</i>
<span class="release-stage" >pre-print</span>
Preserved Fulltext
Text-style transfer aims to convert text given in one domain into another by paraphrasing the sentence or substituting the keywords without altering the content. By necessity, state-of-the-art methods have evolved to accommodate nonparallel training data, as it is frequently the case there are multiple data sources of unequal size, with a mixture of labeled and unlabeled sentences. Moreover, the inherent style defined within each source might be distinct. A generic bidirectional (e.g., formal ⇔
<span class="external-identifiers">
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.10608v1">arXiv:2106.10608v1</a>
<a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/gnoclrbgrnea5oss5odpaujige">fatcat:gnoclrbgrnea5oss5odpaujige</a>
</span>
more »
... informal) style transfer regardless of different groups may not generalize well to different applications. In this work, we developed a task adaptive meta-learning framework that can simultaneously perform a multi-pair text-style transfer using a single model. The proposed method can adaptively balance the difference of meta-knowledge across multiple tasks. Results show that our method leads to better quantitative performance as well as coherent style variations. Common challenges of unbalanced data and mismatched domains are handled well by this method.
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210628232905/https://arxiv.org/pdf/2106.10608v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext">
<button class="ui simple right pointing dropdown compact black labeled icon button serp-button">
<i class="icon ia-icon"></i>
Web Archive
[PDF]
<div class="menu fulltext-thumbnail">
<img src="https://blobs.fatcat.wiki/thumbnail/pdf/c9/80/c980057e6608ac616cea425b6b8c4723fa14e58f.180px.jpg" alt="fulltext thumbnail" loading="lazy">
</div>
</button>
</a>
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.10608v1" title="arxiv.org access">
<button class="ui compact blue labeled icon button serp-button">
<i class="file alternate outline icon"></i>
arxiv.org
</button>
</a>