Robin Kurtz
Department of Computer and Information Science, Linköping University, Sweden
Daniel Roxbo
Department of Computer and Information Science, Linköping University, Sweden
Marco Kuhlmann
Department of Computer and Information Science, Linköping University, Sweden
Download article
Published in: DL4NLP 2019. Proceedings of the First NLPL Workshop on Deep Learning for Natural Language Processing, 30 September, 2019, University of Turku, Turku, Finland
Linköping Electronic Conference Proceedings 163:2, p. 12-21
NEALT Proceedings Series 38:2, p. 12-21
Published: 2019-09-27
ISBN: 978-91-7929-999-6
ISSN: 1650-3686 (print), 1650-3740 (online)
We extend a state-of-the-art deep neural architecture for semantic dependency parsing with features defined over syntactic dependency trees. Our empirical results show that only gold-standard syn tactic information leads to consistent improvements in semantic parsing accuracy, and that the magnitude of these improvements varies with the specific combination of the syntactic and the semantic representation used. In contrast, automatically predicted syntax does not seem to help semantic parsing. Our error analysis suggests that there is a significant overlap between syntactic and semantic representations.
