@inproceedings{howcroft-gkatzia-2023-enunlg,
title = "enunlg: a Python library for reproducible neural data-to-text experimentation",
author = "Howcroft, David M. and
Gkatzia, Dimitra",
editor = "Keet, C. Maria and
Lee, Hung-Yi and
Zarrie{\ss}, Sina",
booktitle = "Proceedings of the 16th International Natural Language Generation Conference: System Demonstrations",
month = sep,
year = "2023",
address = "Prague, Czechia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.inlg-demos.2",
pages = "4--5",
abstract = "Over the past decade, a variety of neural architectures for data-to-text generation (NLG) have been proposed. However, each system typically has its own approach to pre- and post-processing and other implementation details. Diversity in implementations is desirable, but it also confounds attempts to compare model performance: are the differences due to the proposed architectures or are they a byproduct of the libraries used or a result of pre- and post-processing decisions made? To improve reproducibility, we re-implement several pre-Transformer neural models for data-to-text NLG within a single framework to facilitate direct comparisons of the models themselves and better understand the contributions of other design choices. We release our library at https://github.com/NapierNLP/enunlg to serve as a baseline for ongoing work in this area including research on NLG for low-resource languages where transformers might not be optimal.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="howcroft-gkatzia-2023-enunlg">
<titleInfo>
<title>enunlg: a Python library for reproducible neural data-to-text experimentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Howcroft</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dimitra</namePart>
<namePart type="family">Gkatzia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th International Natural Language Generation Conference: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">C</namePart>
<namePart type="given">Maria</namePart>
<namePart type="family">Keet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sina</namePart>
<namePart type="family">Zarrieß</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Prague, Czechia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Over the past decade, a variety of neural architectures for data-to-text generation (NLG) have been proposed. However, each system typically has its own approach to pre- and post-processing and other implementation details. Diversity in implementations is desirable, but it also confounds attempts to compare model performance: are the differences due to the proposed architectures or are they a byproduct of the libraries used or a result of pre- and post-processing decisions made? To improve reproducibility, we re-implement several pre-Transformer neural models for data-to-text NLG within a single framework to facilitate direct comparisons of the models themselves and better understand the contributions of other design choices. We release our library at https://github.com/NapierNLP/enunlg to serve as a baseline for ongoing work in this area including research on NLG for low-resource languages where transformers might not be optimal.</abstract>
<identifier type="citekey">howcroft-gkatzia-2023-enunlg</identifier>
<location>
<url>https://aclanthology.org/2023.inlg-demos.2</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>4</start>
<end>5</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T enunlg: a Python library for reproducible neural data-to-text experimentation
%A Howcroft, David M.
%A Gkatzia, Dimitra
%Y Keet, C. Maria
%Y Lee, Hung-Yi
%Y Zarrieß, Sina
%S Proceedings of the 16th International Natural Language Generation Conference: System Demonstrations
%D 2023
%8 September
%I Association for Computational Linguistics
%C Prague, Czechia
%F howcroft-gkatzia-2023-enunlg
%X Over the past decade, a variety of neural architectures for data-to-text generation (NLG) have been proposed. However, each system typically has its own approach to pre- and post-processing and other implementation details. Diversity in implementations is desirable, but it also confounds attempts to compare model performance: are the differences due to the proposed architectures or are they a byproduct of the libraries used or a result of pre- and post-processing decisions made? To improve reproducibility, we re-implement several pre-Transformer neural models for data-to-text NLG within a single framework to facilitate direct comparisons of the models themselves and better understand the contributions of other design choices. We release our library at https://github.com/NapierNLP/enunlg to serve as a baseline for ongoing work in this area including research on NLG for low-resource languages where transformers might not be optimal.
%U https://aclanthology.org/2023.inlg-demos.2
%P 4-5
Markdown (Informal)
[enunlg: a Python library for reproducible neural data-to-text experimentation](https://aclanthology.org/2023.inlg-demos.2) (Howcroft & Gkatzia, INLG-SIGDIAL 2023)
ACL