Realization of long sentences using chunking

Ewa Muszyńska, Ann Copestake


Abstract
We propose sentence chunking as a way to reduce the time and memory costs of realization of long sentences. During chunking we divide the semantic representation of a sentence into smaller components which can be processed and recombined without loss of information. Our meaning representation of choice is the Dependency Minimal Recursion Semantics (DMRS). We show that realizing chunks of a sentence and combining the results of such realizations increases the coverage for long sentences, significantly reduces the resources required and does not affect the quality of the realization.
Anthology ID:
W17-3533
Volume:
Proceedings of the 10th International Conference on Natural Language Generation
Month:
September
Year:
2017
Address:
Santiago de Compostela, Spain
Editors:
Jose M. Alonso, Alberto Bugarín, Ehud Reiter
Venue:
INLG
SIG:
SIGGEN
Publisher:
Association for Computational Linguistics
Note:
Pages:
218–222
Language:
URL:
https://aclanthology.org/W17-3533
DOI:
10.18653/v1/W17-3533
Bibkey:
Cite (ACL):
Ewa Muszyńska and Ann Copestake. 2017. Realization of long sentences using chunking. In Proceedings of the 10th International Conference on Natural Language Generation, pages 218–222, Santiago de Compostela, Spain. Association for Computational Linguistics.
Cite (Informal):
Realization of long sentences using chunking (Muszyńska & Copestake, INLG 2017)
Copy Citation:
PDF:
https://aclanthology.org/W17-3533.pdf