A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://www.aclweb.org/anthology/W17-4305.pdf">the original URL</a>. The file type is <code>application/pdf</code>.
Syntax Aware LSTM model for Semantic Role Labeling
<span title="">2017</span>
<i title="Association for Computational Linguistics">
<a target="_blank" rel="noopener" href="https://fatcat.wiki/container/u3ideoxy4fghvbsstiknuweth4" style="color: black;">Proceedings of the 2nd Workshop on Structured Prediction for Natural Language Processing</a>
</i>
Preserved Fulltext
In Semantic Role Labeling (SRL) task, the tree structured dependency relation is rich in syntax information, but it is not well handled by existing models. In this paper, we propose Syntax Aware Long Short Time Memory (SA-LSTM). The structure of SA-LSTM changes according to dependency structure of each sentence, so that SA-LSTM can model the whole tree structure of dependency relation in an architecture engineering way. Experiments demonstrate that on Chinese Proposition Bank (CPB) 1.0, SA-LSTM
<span class="external-identifiers">
<a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/w17-4305">doi:10.18653/v1/w17-4305</a>
<a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/emnlp/QianSCLZ17.html">dblp:conf/emnlp/QianSCLZ17</a>
<a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/naettsabzfbe7fa2365p7zsvrm">fatcat:naettsabzfbe7fa2365p7zsvrm</a>
</span>
more »
... improves F 1 by 2.06% than ordinary bi-LSTM with feature engineered dependency relation information, and gives state-of-the-art F 1 of 79.92%. On English CoNLL 2005 dataset, SA-LSTM brings improvement (2.1%) to bi-LSTM model and also brings slight improvement (0.3%) when added to the stateof-the-art model.
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200309054919/https://www.aclweb.org/anthology/W17-4305.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/8e/5f/8e5fbfc5a0fa52f249a3ccaaeb943c6ea8b754bf.180px.jpg" alt="fulltext thumbnail" loading="lazy">
</div>
</button>
</a>
<a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/w17-4305">
<button class="ui left aligned compact blue labeled icon button serp-button">
<i class="external alternate icon"></i>
Publisher / doi.org
</button>
</a>