TY  - CHAP
U1  - Buchbeitrag
A1  - Daza, Angel
A1  - Frank, Anette
ED  - Inui, Kentaro
ED  - Jiang, Jing
ED  - Ng, Vincent
ED  - Wan, Xiaojun
T1  - Translate and label! An encoder-decoder approach for cross-lingual semantic role labeling
T2  - 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
N2  - 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.
KW  - Simultanübersetzen
KW  - Automatische Sprachverarbeitung
KW  - Annotation
KW  - Computerlinguistik
KW  - Semantik
Y1  - 2019
UN  - https://nbn-resolving.org/urn:nbn:de:bsz:mh39-94395
UR  - https://www.aclweb.org/anthology/D19-1056.pdf
UR  - https://www.aclweb.org/anthology/volumes/D19-1/
SN  - 978-1-950737-90-1
SB  - 978-1-950737-90-1
U6  - https://doi.org/10.18653/v1/D19-1056
DO  - https://doi.org/10.18653/v1/D19-1056
SP  - 603
EP  - 615
PB  - The Association for Computational Linguistics
CY  - Stroudsburg, PA, USA
ER  -