Encoder-Decoder Model for Semantic Role Labelingdoi:10.11588/data/TOI9NQheiDATA2020-01-231Daza, Angel, 2020, "Encoder-Decoder Model for Semantic Role Labeling", https://doi.org/10.11588/data/TOI9NQ, heiDATA, V1Encoder-Decoder Model for Semantic Role Labelingdoi:10.11588/data/TOI9NQDaza, Angel2019Leibniz Institute for the German LanguageheiDATADaza, AngelArts and HumanitiesComputer and Information ScienceSemantic Role LabelingSRLmonolingual settingmultilingual settingcross-lingual settingsemantic role annotationSemantic Role Labeling<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>program source code<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>1908.11326<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>README.mdtext/markdownSRL-S2S.zipapplication/zip