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
Editors:
Kees van Deemter, Chenghua Lin, Hiroya Takamura
Venue:
INLG
SIG:
SIGGEN
Publisher:
Association for Computational Linguistics
Note:
Pages:
563–574
Language:
URL:
https://aclanthology.org/W19-8670
DOI:
10.18653/v1/W19-8670
Bibkey:
Cite (ACL):
Ondřej Dušek and Filip Jurčíček. 2019. Neural Generation for Czech: Data and Baselines. In Proceedings of the 12th International Conference on Natural Language Generation, pages 563–574, Tokyo, Japan. Association for Computational Linguistics.
Cite (Informal):
Neural Generation for Czech: Data and Baselines (Dušek & Jurčíček, INLG 2019)
Copy Citation:
PDF:
https://aclanthology.org/W19-8670.pdf