@inproceedings{dusek-jurcicek-2019-neural,
title = "Neural Generation for {C}zech: Data and Baselines",
author = "Du{\v{s}}ek, Ond{\v{r}}ej and
Jur{\v{c}}{\'\i}{\v{c}}ek, Filip",
editor = "van Deemter, Kees and
Lin, Chenghua and
Takamura, Hiroya",
booktitle = "Proceedings of the 12th International Conference on Natural Language Generation",
month = oct # "{--}" # nov,
year = "2019",
address = "Tokyo, Japan",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-8670",
doi = "10.18653/v1/W19-8670",
pages = "563--574",
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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dusek-jurcicek-2019-neural">
<titleInfo>
<title>Neural Generation for Czech: Data and Baselines</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Dušek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Filip</namePart>
<namePart type="family">Jurčíček</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-oct–nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 12th International Conference on Natural Language Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kees</namePart>
<namePart type="family">van Deemter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenghua</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroya</namePart>
<namePart type="family">Takamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Tokyo, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">dusek-jurcicek-2019-neural</identifier>
<identifier type="doi">10.18653/v1/W19-8670</identifier>
<location>
<url>https://aclanthology.org/W19-8670</url>
</location>
<part>
<date>2019-oct–nov</date>
<extent unit="page">
<start>563</start>
<end>574</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Neural Generation for Czech: Data and Baselines
%A Dušek, Ondřej
%A Jurčíček, Filip
%Y van Deemter, Kees
%Y Lin, Chenghua
%Y Takamura, Hiroya
%S Proceedings of the 12th International Conference on Natural Language Generation
%D 2019
%8 oct–nov
%I Association for Computational Linguistics
%C Tokyo, Japan
%F dusek-jurcicek-2019-neural
%X 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.
%R 10.18653/v1/W19-8670
%U https://aclanthology.org/W19-8670
%U https://doi.org/10.18653/v1/W19-8670
%P 563-574
Markdown (Informal)
[Neural Generation for Czech: Data and Baselines](https://aclanthology.org/W19-8670) (Dušek & Jurčíček, INLG 2019)
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.