10.11588/data/TOI9NQDaza, AngelAngelDazaLeibniz Institute for the German LanguageEncoder-Decoder Model for Semantic Role LabelingheiDATA2020Arts and HumanitiesComputer and Information ScienceSemantic Role LabelingSRLmonolingual settingmultilingual settingcross-lingual settingsemantic role annotationSemantic Role LabelingDaza, AngelAngelDazaLeibniz Institute for the German Language20192020-01-23program source code1908.11326858044537016text/markdownapplication/zip1.0<p><strong>Abstract (Daza &amp; 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>Leibniz Institute for the German Language