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://www.aclweb.org/anthology/D19-1438.pdf">the original URL</a>. The file type is <code>application/pdf</code>.
Compositional Generalization for Primitive Substitutions
<span title="">2019</span>
<i title="Association for Computational Linguistics">
<a target="_blank" rel="noopener" href="https://fatcat.wiki/container/u3ideoxy4fghvbsstiknuweth4" style="color: black;">Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)</a>
</i>
Preserved Fulltext
Compositional generalization is a basic mechanism in human language learning, but current neural networks lack such ability. In this paper, we conduct fundamental research for encoding compositionality in neural networks. Conventional methods use a single representation for the input sentence, making it hard to apply prior knowledge of compositionality. In contrast, our approach leverages such knowledge with two representations, one generating attention maps, and the other mapping attended
<span class="external-identifiers">
<a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/d19-1438">doi:10.18653/v1/d19-1438</a>
<a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/emnlp/LiZWH19.html">dblp:conf/emnlp/LiZWH19</a>
<a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nx7jm6it65gbdavc56o6gt3edm">fatcat:nx7jm6it65gbdavc56o6gt3edm</a>
</span>
more »
... words to output symbols. We reduce the entropy in each representation to improve generalization. Our experiments demonstrate significant improvements over the conventional methods in five NLP tasks including instruction learning and machine translation. In the SCAN domain, it boosts accuracies from 14.0% to 98.8% in Jump task, and from 92.0% to 99.7% in TurnLeft task. It also beats human performance on a few-shot learning task. We hope the proposed approach can help ease future research towards human-level compositional language learning. Source code is available online 1 .
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191203111243/https://www.aclweb.org/anthology/D19-1438.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/fb/7f/fb7f55ea266483bc366b086d5094e088d05acf4f.180px.jpg" alt="fulltext thumbnail" loading="lazy">
</div>
</button>
</a>
<a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/d19-1438">
<button class="ui left aligned compact blue labeled icon button serp-button">
<i class="external alternate icon"></i>
Publisher / doi.org
</button>
</a>