@inproceedings{buchholz-etal-2024-bootstrapping,
title = "Bootstrapping {UMR} Annotations for {A}rapaho from Language Documentation Resources",
author = "Buchholz, Matthew J. and
Bonn, Julia and
Post, Claire Benet and
Cowell, Andrew and
Palmer, Alexis",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.220",
pages = "2447--2457",
abstract = "Uniform Meaning Representation (UMR) is a semantic labeling system in the AMR family designed to be uniformly applicable to typologically diverse languages. The UMR labeling system is quite thorough and can be time-consuming to execute, especially if annotators are starting from scratch. In this paper, we focus on methods for bootstrapping UMR annotations for a given language from existing resources, and specifically from typical products of language documentation work, such as lexical databases and interlinear glossed text (IGT). Using Arapaho as our test case, we present and evaluate a bootstrapping process that automatically generates UMR subgraphs from IGT. Additionally, we describe and evaluate a method for bootstrapping valency lexicon entries from lexical databases for both the target language and English. We are able to generate enough basic structure in UMR graphs from the existing Arapaho interlinearized texts to automate UMR labeling to a significant extent. Our method thus has the potential to streamline the process of building meaning representations for new languages without existing large-scale computational resources.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="buchholz-etal-2024-bootstrapping">
<titleInfo>
<title>Bootstrapping UMR Annotations for Arapaho from Language Documentation Resources</title>
</titleInfo>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="given">J</namePart>
<namePart type="family">Buchholz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="family">Bonn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claire</namePart>
<namePart type="given">Benet</namePart>
<namePart type="family">Post</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Cowell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Uniform Meaning Representation (UMR) is a semantic labeling system in the AMR family designed to be uniformly applicable to typologically diverse languages. The UMR labeling system is quite thorough and can be time-consuming to execute, especially if annotators are starting from scratch. In this paper, we focus on methods for bootstrapping UMR annotations for a given language from existing resources, and specifically from typical products of language documentation work, such as lexical databases and interlinear glossed text (IGT). Using Arapaho as our test case, we present and evaluate a bootstrapping process that automatically generates UMR subgraphs from IGT. Additionally, we describe and evaluate a method for bootstrapping valency lexicon entries from lexical databases for both the target language and English. We are able to generate enough basic structure in UMR graphs from the existing Arapaho interlinearized texts to automate UMR labeling to a significant extent. Our method thus has the potential to streamline the process of building meaning representations for new languages without existing large-scale computational resources.</abstract>
<identifier type="citekey">buchholz-etal-2024-bootstrapping</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.220</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>2447</start>
<end>2457</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bootstrapping UMR Annotations for Arapaho from Language Documentation Resources
%A Buchholz, Matthew J.
%A Bonn, Julia
%A Post, Claire Benet
%A Cowell, Andrew
%A Palmer, Alexis
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F buchholz-etal-2024-bootstrapping
%X Uniform Meaning Representation (UMR) is a semantic labeling system in the AMR family designed to be uniformly applicable to typologically diverse languages. The UMR labeling system is quite thorough and can be time-consuming to execute, especially if annotators are starting from scratch. In this paper, we focus on methods for bootstrapping UMR annotations for a given language from existing resources, and specifically from typical products of language documentation work, such as lexical databases and interlinear glossed text (IGT). Using Arapaho as our test case, we present and evaluate a bootstrapping process that automatically generates UMR subgraphs from IGT. Additionally, we describe and evaluate a method for bootstrapping valency lexicon entries from lexical databases for both the target language and English. We are able to generate enough basic structure in UMR graphs from the existing Arapaho interlinearized texts to automate UMR labeling to a significant extent. Our method thus has the potential to streamline the process of building meaning representations for new languages without existing large-scale computational resources.
%U https://aclanthology.org/2024.lrec-main.220
%P 2447-2457
Markdown (Informal)
[Bootstrapping UMR Annotations for Arapaho from Language Documentation Resources](https://aclanthology.org/2024.lrec-main.220) (Buchholz et al., LREC-COLING 2024)
ACL