Surface Realisation Using Full Delexicalisation

Anastasia Shimorina, Claire Gardent


Abstract
Surface realisation (SR) maps a meaning representation to a sentence and can be viewed as consisting of three subtasks: word ordering, morphological inflection and contraction generation (e.g., clitic attachment in Portuguese or elision in French). We propose a modular approach to surface realisation which models each of these components separately, and evaluate our approach on the 10 languages covered by the SR’18 Surface Realisation Shared Task shallow track. We provide a detailed evaluation of how word order, morphological realisation and contractions are handled by the model and an analysis of the differences in word ordering performance across languages.
Anthology ID:
D19-1305
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
3086–3096
Language:
URL:
https://www.aclweb.org/anthology/D19-1305
DOI:
10.18653/v1/D19-1305
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/D19-1305.pdf
Attachment:
 D19-1305.Attachment.zip