@inproceedings{howcroft-gkatzia-2022-nlg,
title = "Most {NLG} is Low-Resource: here{'}s what we can do about it",
author = "Howcroft, David M. and
Gkatzia, Dimitra",
editor = "Bosselut, Antoine and
Chandu, Khyathi and
Dhole, Kaustubh and
Gangal, Varun and
Gehrmann, Sebastian and
Jernite, Yacine and
Novikova, Jekaterina and
Perez-Beltrachini, Laura",
booktitle = "Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM)",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.gem-1.29",
doi = "10.18653/v1/2022.gem-1.29",
pages = "336--350",
abstract = "Many domains and tasks in natural language generation (NLG) are inherently {`}low-resource{'}, where training data, tools and linguistic analyses are scarce. This poses a particular challenge to researchers and system developers in the era of machine-learning-driven NLG. In this position paper, we initially present the challenges researchers {\&} developers often encounter when dealing with low-resource settings in NLG. We then argue that it is unsustainable to collect large aligned datasets or build large language models from scratch for every possible domain due to cost, labour, and time constraints, so researching and developing methods and resources for low-resource settings is vital. We then discuss current approaches to low-resource NLG, followed by proposed solutions and promising avenues for future work in NLG for low-resource settings.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="howcroft-gkatzia-2022-nlg">
<titleInfo>
<title>Most NLG is Low-Resource: here’s what we can do about it</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>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Antoine</namePart>
<namePart type="family">Bosselut</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khyathi</namePart>
<namePart type="family">Chandu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaustubh</namePart>
<namePart type="family">Dhole</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Varun</namePart>
<namePart type="family">Gangal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Gehrmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yacine</namePart>
<namePart type="family">Jernite</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jekaterina</namePart>
<namePart type="family">Novikova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="family">Perez-Beltrachini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Many domains and tasks in natural language generation (NLG) are inherently ‘low-resource’, where training data, tools and linguistic analyses are scarce. This poses a particular challenge to researchers and system developers in the era of machine-learning-driven NLG. In this position paper, we initially present the challenges researchers & developers often encounter when dealing with low-resource settings in NLG. We then argue that it is unsustainable to collect large aligned datasets or build large language models from scratch for every possible domain due to cost, labour, and time constraints, so researching and developing methods and resources for low-resource settings is vital. We then discuss current approaches to low-resource NLG, followed by proposed solutions and promising avenues for future work in NLG for low-resource settings.</abstract>
<identifier type="citekey">howcroft-gkatzia-2022-nlg</identifier>
<identifier type="doi">10.18653/v1/2022.gem-1.29</identifier>
<location>
<url>https://aclanthology.org/2022.gem-1.29</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>336</start>
<end>350</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Most NLG is Low-Resource: here’s what we can do about it
%A Howcroft, David M.
%A Gkatzia, Dimitra
%Y Bosselut, Antoine
%Y Chandu, Khyathi
%Y Dhole, Kaustubh
%Y Gangal, Varun
%Y Gehrmann, Sebastian
%Y Jernite, Yacine
%Y Novikova, Jekaterina
%Y Perez-Beltrachini, Laura
%S Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM)
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Hybrid)
%F howcroft-gkatzia-2022-nlg
%X Many domains and tasks in natural language generation (NLG) are inherently ‘low-resource’, where training data, tools and linguistic analyses are scarce. This poses a particular challenge to researchers and system developers in the era of machine-learning-driven NLG. In this position paper, we initially present the challenges researchers & developers often encounter when dealing with low-resource settings in NLG. We then argue that it is unsustainable to collect large aligned datasets or build large language models from scratch for every possible domain due to cost, labour, and time constraints, so researching and developing methods and resources for low-resource settings is vital. We then discuss current approaches to low-resource NLG, followed by proposed solutions and promising avenues for future work in NLG for low-resource settings.
%R 10.18653/v1/2022.gem-1.29
%U https://aclanthology.org/2022.gem-1.29
%U https://doi.org/10.18653/v1/2022.gem-1.29
%P 336-350
Markdown (Informal)
[Most NLG is Low-Resource: here’s what we can do about it](https://aclanthology.org/2022.gem-1.29) (Howcroft & Gkatzia, GEM 2022)
ACL
- David M. Howcroft and Dimitra Gkatzia. 2022. Most NLG is Low-Resource: here’s what we can do about it. In Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM), pages 336–350, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.