Deciphering Undersegmented Ancient Scripts Using Phonetic Prior

Luo, Jiaming; Hartmann, Frederik; Santus, Enrico; Barzilay, Regina; Cao, Yuan

Deciphering Undersegmented Ancient Scripts Using Phonetic Prior

Dateien

Luo_2-74mf4c553nsp9.pdfGröße: 678.46 KBDownloads: 87

Datum

2021

Autor:innen

Luo, Jiaming

Hartmann, Frederik

Santus, Enrico

Barzilay, Regina

Cao, Yuan

Open Access-Veröffentlichung

Open Access Gold

Sammlungen

Linguistik

Publikationstyp

Zeitschriftenartikel

Publikationsstatus

Published

Erschienen in

Transactions of the Association for Computational Linguistics. MIT Press. 2021, 9, pp. 69-81. eISSN 2307-387X. Available under: doi: 10.1162/tacl_a_00354

Zusammenfassung

Most undeciphered lost languages exhibit two characteristics that pose significant decipherment challenges: (1) the scripts are not fully segmented into words; (2) the closest known language is not determined. We propose a decipherment model that handles both of these challenges by building on rich linguistic constraints reflecting consistent patterns in historical sound change. We capture the natural phonological geometry by learning character embeddings based on the International Phonetic Alphabet (IPA). The resulting generative framework jointly models word segmentation and cognate alignment, informed by phonological constraints. We evaluate the model on both deciphered languages (Gothic, Ugaritic) and an undeciphered one (Iberian). The experiments show that incorporating phonetic geometry leads to clear and consistent gains. Additionally, we propose a measure for language closeness which correctly identifies related languages for Gothic and Ugaritic. For Iberian, the method does not show strong evidence supporting Basque as a related language, concurring with the favored position by the current scholarship.1

Fachgebiet (DDC)

400 Sprachwissenschaft, Linguistik

Zitieren

ISO 690

LUO, Jiaming, Frederik HARTMANN, Enrico SANTUS, Regina BARZILAY, Yuan CAO, 2021. Deciphering Undersegmented Ancient Scripts Using Phonetic Prior. In: Transactions of the Association for Computational Linguistics. MIT Press. 2021, 9, pp. 69-81. eISSN 2307-387X. Available under: doi: 10.1162/tacl_a_00354

BibTex

@article{Luo2021Decip-57257,
  year={2021},
  doi={10.1162/tacl_a_00354},
  title={Deciphering Undersegmented Ancient Scripts Using Phonetic Prior},
  volume={9},
  journal={Transactions of the Association for Computational Linguistics},
  pages={69--81},
  author={Luo, Jiaming and Hartmann, Frederik and Santus, Enrico and Barzilay, Regina and Cao, Yuan}
}

RDF

<rdf:RDF
    xmlns:dcterms="http://purl.org/dc/terms/"
    xmlns:dc="http://purl.org/dc/elements/1.1/"
    xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
    xmlns:bibo="http://purl.org/ontology/bibo/"
    xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#"
    xmlns:foaf="http://xmlns.com/foaf/0.1/"
    xmlns:void="http://rdfs.org/ns/void#"
    xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > 
  <rdf:Description rdf:about="https://kops.uni-konstanz.de/server/rdf/resource/123456789/57257">
    <dc:contributor>Luo, Jiaming</dc:contributor>
    <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/57257/1/Luo_2-74mf4c553nsp9.pdf"/>
    <dc:creator>Cao, Yuan</dc:creator>
    <dcterms:issued>2021</dcterms:issued>
    <dc:language>eng</dc:language>
    <dc:contributor>Hartmann, Frederik</dc:contributor>
    <dcterms:title>Deciphering Undersegmented Ancient Scripts Using Phonetic Prior</dcterms:title>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/45"/>
    <dcterms:abstract xml:lang="eng">Most undeciphered lost languages exhibit two characteristics that pose significant decipherment challenges: (1) the scripts are not fully segmented into words; (2) the closest known language is not determined. We propose a decipherment model that handles both of these challenges by building on rich linguistic constraints reflecting consistent patterns in historical sound change. We capture the natural phonological geometry by learning character embeddings based on the International Phonetic Alphabet (IPA). The resulting generative framework jointly models word segmentation and cognate alignment, informed by phonological constraints. We evaluate the model on both deciphered languages (Gothic, Ugaritic) and an undeciphered one (Iberian). The experiments show that incorporating phonetic geometry leads to clear and consistent gains. Additionally, we propose a measure for language closeness which correctly identifies related languages for Gothic and Ugaritic. For Iberian, the method does not show strong evidence supporting Basque as a related language, concurring with the favored position by the current scholarship.1</dcterms:abstract>
    <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/57257/1/Luo_2-74mf4c553nsp9.pdf"/>
    <dc:contributor>Barzilay, Regina</dc:contributor>
    <dc:contributor>Cao, Yuan</dc:contributor>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2022-04-11T14:42:07Z</dc:date>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/57257"/>
    <dc:creator>Barzilay, Regina</dc:creator>
    <dc:rights>terms-of-use</dc:rights>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
    <dc:contributor>Santus, Enrico</dc:contributor>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dc:creator>Hartmann, Frederik</dc:creator>
    <dc:creator>Santus, Enrico</dc:creator>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2022-04-11T14:42:07Z</dcterms:available>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/45"/>
    <dc:creator>Luo, Jiaming</dc:creator>
  </rdf:Description>
</rdf:RDF>

Universitätsbibliographie

Ja

Begutachtet

Ja