A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/1901.08014v2.pdf">the original URL</a>. The file type is <code>application/pdf</code>.
Sentiment and Sarcasm Classification with Multitask Learning
[article]
<span title="2019-03-09">2019</span>
<i >
arXiv
</i>
<span class="release-stage" >pre-print</span>
Preserved Fulltext
Other Versions
<span title="2019-01-23">2019</span>
<span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1901.08014v1">arXiv:1901.08014v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/irgoleimvvfghm67gaa6egqx2u">fatcat:irgoleimvvfghm67gaa6egqx2u</a> </span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1901.08014v1">arXiv:1901.08014v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/irgoleimvvfghm67gaa6egqx2u">fatcat:irgoleimvvfghm67gaa6egqx2u</a> </span>
Sentiment classification and sarcasm detection are both important natural language processing (NLP) tasks. Sentiment is always coupled with sarcasm where intensive emotion is expressed. Nevertheless, most literature considers them as two separate tasks. We argue that knowledge in sarcasm detection can also be beneficial to sentiment classification and vice versa. We show that these two tasks are correlated, and present a multi-task learning-based framework using a deep neural network that
<span class="external-identifiers">
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1901.08014v2">arXiv:1901.08014v2</a>
<a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/sgiymzqbhzfv3gfrzwrzp7u7im">fatcat:sgiymzqbhzfv3gfrzwrzp7u7im</a>
</span>
more »
... this correlation to improve the performance of both tasks in a multi-task learning setting. Our method outperforms the state of the art by 3-4% in the benchmark dataset.
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191014070737/https://arxiv.org/pdf/1901.08014v2.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/83/07/830754278255096efb2a61a48b9ceb8ded20d4ab.180px.jpg" alt="fulltext thumbnail" loading="lazy">
</div>
</button>
</a>
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1901.08014v2" 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>