Neural Generation for Czech: Data and Baselines

Ondřej Dušek, Filip Jurčíček


Abstract
We present the first dataset targeted at end-to-end NLG in Czech in the restaurant domain, along with several strong baseline models using the sequence-to-sequence approach. While non-English NLG is under-explored in general, Czech, as a morphologically rich language, makes the task even harder: Since Czech requires inflecting named entities, delexicalization or copy mechanisms do not work out-of-the-box and lexicalizing the generated outputs is non-trivial. In our experiments, we present two different approaches to this this problem: (1) using a neural language model to select the correct inflected form while lexicalizing, (2) a two-step generation setup: our sequence-to-sequence model generates an interleaved sequence of lemmas and morphological tags, which are then inflected by a morphological generator.
Anthology ID:
W19-8670
Volume:
Proceedings of the 12th International Conference on Natural Language Generation
Month:
October–November
Year:
2019
Address:
Tokyo, Japan
Venues:
INLG | WS
SIG:
SIGGEN
Publisher:
Association for Computational Linguistics
Note:
Pages:
563–574
Language:
URL:
https://www.aclweb.org/anthology/W19-8670
DOI:
10.18653/v1/W19-8670
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/W19-8670.pdf