Encoder-Decoder Model for Semantic Role Labelinghttps://doi.org/10.11588/data/TOI9NQDaza, AngelheiDATA2020-01-232020-01-23T10:33:34Z<p><strong>Abstract (Daza & Frank 2019):</strong></p>
<p>We propose a Cross-lingual Encoder-Decoder model that simultaneously translates and generates sentences with Semantic Role Labeling annotations in a resource-poor target language. Unlike annotation projection techniques, our model does not need parallel data during inference time. Our approach can be applied in monolingual, multilingual and cross-lingual settings and is able to produce dependency-based and span-based SRL annotations. We benchmark the labeling performance of our model in different monolingual and multilingual settings using well-known SRL datasets. We then train our model in a cross-lingual setting to generate new SRL labeled data. Finally, we measure the effectiveness of our method by using the generated data to augment the training basis for resource-poor languages and perform manual evaluation to show that it produces high-quality sentences and assigns accurate semantic role annotations. Our proposed architecture offers a flexible method for leveraging SRL data in multiple languages.</p>Arts and HumanitiesComputer and Information ScienceSemantic Role LabelingSRLmonolingual settingmultilingual settingcross-lingual settingsemantic role annotation<p>Daza, Angel and Frank, Anette (2019). Translate and label! An encoder-decoder approach for cross-lingual semantic role labeling. In <em>Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing</em>, November 3-7, 2019, Hong Kong, China.</p>, arXiv, 1908.11326, https://arxiv.org/abs/1908.113262019program source codeLicensed under <a href="https://www.gnu.org/licenses/gpl-3.0.en.html">General Public License v3 (GPL v3)</a>.
<p>Please note the licenses of required components:</p>
<ul>
<li><a href="https://github.com/allenai/allennlp"><strong>AllenNLP 0.8.2</strong></a> (Apache License 2.0)</li>
<li><strong><a href="https://github.com/zalandoresearch/flair">Flair 0.4.3</a> </strong>(MIT License)</li>
<li><a href="https://www.python.org/downloads/source/"><strong>Python 3.6</strong></a> (<a href="https://docs.python.org/3/license.html#licenses-and-acknowledgements-for-incorporated-software">Open Source</a>)</li>
<li><strong><a href="https://pytorch.org/%20">pytorch 1.0</a></strong> licenses (Berkeley Software Distribution licence)</li>
</ul>