The DipInfoUniTo Realizer at SRST’19: Learning to Rank and Deep Morphology Prediction for Multilingual Surface Realization

Alessandro Mazzei, Valerio Basile


Abstract
We describe the system presented at the SR’19 shared task by the DipInfoUnito team. Our approach is based on supervised machine learning. In particular, we divide the SR task into two independent subtasks, namely word order prediction and morphology inflection prediction. Two neural networks with different architectures run on the same input structure, each producing a partial output which is recombined in the final step in order to produce the predicted surface form. This work is a direct successor of the architecture presented at SR’19.
Anthology ID:
D19-6311
Volume:
Proceedings of the 2nd Workshop on Multilingual Surface Realisation (MSR 2019)
Month:
November
Year:
2019
Address:
Hong Kong, China
Venues:
EMNLP | WS
SIG:
SIGGEN
Publisher:
Association for Computational Linguistics
Note:
Pages:
81–87
Language:
URL:
https://aclanthology.org/D19-6311
DOI:
10.18653/v1/D19-6311
Bibkey:
Cite (ACL):
Alessandro Mazzei and Valerio Basile. 2019. The DipInfoUniTo Realizer at SRST’19: Learning to Rank and Deep Morphology Prediction for Multilingual Surface Realization. In Proceedings of the 2nd Workshop on Multilingual Surface Realisation (MSR 2019), pages 81–87, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
The DipInfoUniTo Realizer at SRST’19: Learning to Rank and Deep Morphology Prediction for Multilingual Surface Realization (Mazzei & Basile, EMNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-6311.pdf