Volltext-Downloads (blau) und Frontdoor-Views (grau)

Translate and label! An encoder-decoder approach for cross-lingual semantic role labeling

  • 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 dependencybased 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.

Export metadata

Additional Services

Search Google Scholar


Author:Angel Daza, Anette Frank
Parent Title (English):Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), 3.–7. November 2019, Hong Kong, China
Publisher:The Association for Computational Linguistics
Place of publication:Stroudsburg, PA, USA
Editor:Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Document Type:Part of a Book
Year of first Publication:2019
Date of Publication (online):2019/12/11
GND Keyword:Annotation; Automatische Sprachverarbeitung; Computerlinguistik; Semantik; Simultanübersetzen
First Page:603
Last Page:615
DDC classes:400 Sprache / 400 Sprache, Linguistik
Open Access?:ja
Leibniz-Classification:Sprache, Linguistik
Program areas:Digitale Sprachwissenschaft
Licence (German):License LogoCreative Commons - CC BY - Namensnennung 4.0 International