@inproceedings{kale-roy-2020-machine,
title = "Machine Translation Pre-training for Data-to-Text Generation - A Case Study in {C}zech",
author = "Kale, Mihir and
Roy, Scott",
editor = "Davis, Brian and
Graham, Yvette and
Kelleher, John and
Sripada, Yaji",
booktitle = "Proceedings of the 13th International Conference on Natural Language Generation",
month = dec,
year = "2020",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.inlg-1.13",
doi = "10.18653/v1/2020.inlg-1.13",
pages = "91--96",
abstract = "While there is a large body of research studying deep learning methods for text generation from structured data, almost all of it focuses purely on English. In this paper, we study the effectiveness of machine translation based pre-training for data-to-text generation in non-English languages. Since the structured data is generally expressed in English, text generation into other languages involves elements of translation, transliteration and copying - elements already encoded in neural machine translation systems. Moreover, since data-to-text corpora are typically small, this task can benefit greatly from pre-training. We conduct experiments on Czech, a morphologically complex language. Results show that machine translation pre-training lets us train endto-end models that significantly improve upon unsupervised pre-training and linguistically informed pipelined neural systems, as judged by automatic metrics and human evaluation. We also show that this approach enjoys several desirable properties, including improved performance in low data scenarios and applicability to low resource languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kale-roy-2020-machine">
<titleInfo>
<title>Machine Translation Pre-training for Data-to-Text Generation - A Case Study in Czech</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mihir</namePart>
<namePart type="family">Kale</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="family">Roy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 13th International Conference on Natural Language Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Brian</namePart>
<namePart type="family">Davis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Kelleher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaji</namePart>
<namePart type="family">Sripada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>While there is a large body of research studying deep learning methods for text generation from structured data, almost all of it focuses purely on English. In this paper, we study the effectiveness of machine translation based pre-training for data-to-text generation in non-English languages. Since the structured data is generally expressed in English, text generation into other languages involves elements of translation, transliteration and copying - elements already encoded in neural machine translation systems. Moreover, since data-to-text corpora are typically small, this task can benefit greatly from pre-training. We conduct experiments on Czech, a morphologically complex language. Results show that machine translation pre-training lets us train endto-end models that significantly improve upon unsupervised pre-training and linguistically informed pipelined neural systems, as judged by automatic metrics and human evaluation. We also show that this approach enjoys several desirable properties, including improved performance in low data scenarios and applicability to low resource languages.</abstract>
<identifier type="citekey">kale-roy-2020-machine</identifier>
<identifier type="doi">10.18653/v1/2020.inlg-1.13</identifier>
<location>
<url>https://aclanthology.org/2020.inlg-1.13</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>91</start>
<end>96</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Machine Translation Pre-training for Data-to-Text Generation - A Case Study in Czech
%A Kale, Mihir
%A Roy, Scott
%Y Davis, Brian
%Y Graham, Yvette
%Y Kelleher, John
%Y Sripada, Yaji
%S Proceedings of the 13th International Conference on Natural Language Generation
%D 2020
%8 December
%I Association for Computational Linguistics
%C Dublin, Ireland
%F kale-roy-2020-machine
%X While there is a large body of research studying deep learning methods for text generation from structured data, almost all of it focuses purely on English. In this paper, we study the effectiveness of machine translation based pre-training for data-to-text generation in non-English languages. Since the structured data is generally expressed in English, text generation into other languages involves elements of translation, transliteration and copying - elements already encoded in neural machine translation systems. Moreover, since data-to-text corpora are typically small, this task can benefit greatly from pre-training. We conduct experiments on Czech, a morphologically complex language. Results show that machine translation pre-training lets us train endto-end models that significantly improve upon unsupervised pre-training and linguistically informed pipelined neural systems, as judged by automatic metrics and human evaluation. We also show that this approach enjoys several desirable properties, including improved performance in low data scenarios and applicability to low resource languages.
%R 10.18653/v1/2020.inlg-1.13
%U https://aclanthology.org/2020.inlg-1.13
%U https://doi.org/10.18653/v1/2020.inlg-1.13
%P 91-96
Markdown (Informal)
[Machine Translation Pre-training for Data-to-Text Generation - A Case Study in Czech](https://aclanthology.org/2020.inlg-1.13) (Kale & Roy, INLG 2020)
ACL