@inproceedings{chandu-etal-2023-lowrecorp,
title = "{LOWRECORP}: the Low-Resource {NLG} Corpus Building Challenge",
author = "Chandu, Khyathi Raghavi and
Howcroft, David M. and
Gkatzia, Dimitra and
Chung, Yi-Ling and
Hou, Yufang and
Emezue, Chris Chinenye and
Rajpoot, Pawan and
Adewumi, Tosin",
editor = "Mille, Simon",
booktitle = "Proceedings of the 16th International Natural Language Generation Conference: Generation Challenges",
month = sep,
year = "2023",
address = "Prague, Czechia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.inlg-genchal.1",
pages = "1--9",
abstract = "Most languages in the world do not have sufficient data available to develop neural-network-based natural language generation (NLG) systems. To alleviate this resource scarcity, we propose a novel challenge for the NLG community: low-resource language corpus development (LOWRECORP). We present an innovative framework to collect a single dataset with dual tasks to maximize the efficiency of data collection efforts and respect language consultant time. Specifically, we focus on a text-chat-based interface for two generation tasks {--} conversational response generation grounded in a source document and/or image and dialogue summarization (from the former task). The goal of this shared task is to collectively develop grounded datasets for local and low-resourced languages. To enable data collection, we make available web-based software that can be used to collect these grounded conversations and summaries. Submissions will be assessed for the size, complexity, and diversity of the corpora to ensure quality control of the datasets as well as any enhancements to the interface or novel approaches to grounding conversations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chandu-etal-2023-lowrecorp">
<titleInfo>
<title>LOWRECORP: the Low-Resource NLG Corpus Building Challenge</title>
</titleInfo>
<name type="personal">
<namePart type="given">Khyathi</namePart>
<namePart type="given">Raghavi</namePart>
<namePart type="family">Chandu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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>
<name type="personal">
<namePart type="given">Yi-Ling</namePart>
<namePart type="family">Chung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yufang</namePart>
<namePart type="family">Hou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="given">Chinenye</namePart>
<namePart type="family">Emezue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pawan</namePart>
<namePart type="family">Rajpoot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tosin</namePart>
<namePart type="family">Adewumi</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: Generation Challenges</title>
</titleInfo>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Mille</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>Most languages in the world do not have sufficient data available to develop neural-network-based natural language generation (NLG) systems. To alleviate this resource scarcity, we propose a novel challenge for the NLG community: low-resource language corpus development (LOWRECORP). We present an innovative framework to collect a single dataset with dual tasks to maximize the efficiency of data collection efforts and respect language consultant time. Specifically, we focus on a text-chat-based interface for two generation tasks – conversational response generation grounded in a source document and/or image and dialogue summarization (from the former task). The goal of this shared task is to collectively develop grounded datasets for local and low-resourced languages. To enable data collection, we make available web-based software that can be used to collect these grounded conversations and summaries. Submissions will be assessed for the size, complexity, and diversity of the corpora to ensure quality control of the datasets as well as any enhancements to the interface or novel approaches to grounding conversations.</abstract>
<identifier type="citekey">chandu-etal-2023-lowrecorp</identifier>
<location>
<url>https://aclanthology.org/2023.inlg-genchal.1</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>1</start>
<end>9</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LOWRECORP: the Low-Resource NLG Corpus Building Challenge
%A Chandu, Khyathi Raghavi
%A Howcroft, David M.
%A Gkatzia, Dimitra
%A Chung, Yi-Ling
%A Hou, Yufang
%A Emezue, Chris Chinenye
%A Rajpoot, Pawan
%A Adewumi, Tosin
%Y Mille, Simon
%S Proceedings of the 16th International Natural Language Generation Conference: Generation Challenges
%D 2023
%8 September
%I Association for Computational Linguistics
%C Prague, Czechia
%F chandu-etal-2023-lowrecorp
%X Most languages in the world do not have sufficient data available to develop neural-network-based natural language generation (NLG) systems. To alleviate this resource scarcity, we propose a novel challenge for the NLG community: low-resource language corpus development (LOWRECORP). We present an innovative framework to collect a single dataset with dual tasks to maximize the efficiency of data collection efforts and respect language consultant time. Specifically, we focus on a text-chat-based interface for two generation tasks – conversational response generation grounded in a source document and/or image and dialogue summarization (from the former task). The goal of this shared task is to collectively develop grounded datasets for local and low-resourced languages. To enable data collection, we make available web-based software that can be used to collect these grounded conversations and summaries. Submissions will be assessed for the size, complexity, and diversity of the corpora to ensure quality control of the datasets as well as any enhancements to the interface or novel approaches to grounding conversations.
%U https://aclanthology.org/2023.inlg-genchal.1
%P 1-9
Markdown (Informal)
[LOWRECORP: the Low-Resource NLG Corpus Building Challenge](https://aclanthology.org/2023.inlg-genchal.1) (Chandu et al., INLG-SIGDIAL 2023)
ACL
- Khyathi Raghavi Chandu, David M. Howcroft, Dimitra Gkatzia, Yi-Ling Chung, Yufang Hou, Chris Chinenye Emezue, Pawan Rajpoot, and Tosin Adewumi. 2023. LOWRECORP: the Low-Resource NLG Corpus Building Challenge. In Proceedings of the 16th International Natural Language Generation Conference: Generation Challenges, pages 1–9, Prague, Czechia. Association for Computational Linguistics.