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://arxiv.org/pdf/1701.02593v2.pdf">the original URL</a>. The file type is <code>application/pdf</code>.
A Simple and Accurate Syntax-Agnostic Neural Model for Dependency-based Semantic Role Labeling
[article]
<span title="2017-06-15">2017</span>
<i >
arXiv
</i>
<span class="release-stage" >pre-print</span>
Preserved Fulltext
Other Versions
<span title="2017-01-10">2017</span>
<span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1701.02593v1">arXiv:1701.02593v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6drl7mvusvfuvmlqkshmkrfhpy">fatcat:6drl7mvusvfuvmlqkshmkrfhpy</a> </span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1701.02593v1">arXiv:1701.02593v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6drl7mvusvfuvmlqkshmkrfhpy">fatcat:6drl7mvusvfuvmlqkshmkrfhpy</a> </span>
We introduce a simple and accurate neural model for dependency-based semantic role labeling. Our model predicts predicate-argument dependencies relying on states of a bidirectional LSTM encoder. The semantic role labeler achieves competitive performance on English, even without any kind of syntactic information and only using local inference. However, when automatically predicted part-of-speech tags are provided as input, it substantially outperforms all previous local models and approaches the
<span class="external-identifiers">
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1701.02593v2">arXiv:1701.02593v2</a>
<a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6stapn4sojej3lhg373wc5mbau">fatcat:6stapn4sojej3lhg373wc5mbau</a>
</span>
more »
... best reported results on the English CoNLL-2009 dataset. We also consider Chinese, Czech and Spanish where our approach also achieves competitive results. Syntactic parsers are unreliable on out-of-domain data, so standard (i.e., syntactically-informed) SRL models are hindered when tested in this setting. Our syntax-agnostic model appears more robust, resulting in the best reported results on standard out-of-domain test sets.
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201001013438/https://arxiv.org/pdf/1701.02593v2.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/a1/c1/a1c11b5a338c8007230b4822145b667ee3f00568.180px.jpg" alt="fulltext thumbnail" loading="lazy">
</div>
</button>
</a>
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1701.02593v2" 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>