<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fourrier-sagot-2020-comparing">
    <titleInfo>
        <title>Comparing Statistical and Neural Models for Learning Sound Correspondences</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Clémentine</namePart>
        <namePart type="family">Fourrier</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Benoît</namePart>
        <namePart type="family">Sagot</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <language>
        <languageTerm type="text">English</languageTerm>
        <languageTerm type="code" authority="iso639-2b">eng</languageTerm>
    </language>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of LT4HALA 2020 - 1st Workshop on Language Technologies for Historical and Ancient Languages</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Rachele</namePart>
            <namePart type="family">Sprugnoli</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Marco</namePart>
            <namePart type="family">Passarotti</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>European Language Resources Association (ELRA)</publisher>
            <place>
                <placeTerm type="text">Marseille, France</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-10-95546-53-5</identifier>
    </relatedItem>
    <abstract>Cognate prediction and proto-form reconstruction are key tasks in computational historical linguistics that rely on the study of sound change regularity. Solving these tasks appears to be very similar to machine translation, though methods from that field have barely been applied to historical linguistics. Therefore, in this paper, we investigate the learnability of sound correspondences between a proto-language and daughter languages for two machine-translation-inspired models, one statistical, the other neural. We first carry out our experiments on plausible artificial languages, without noise, in order to study the role of each parameter on the algorithms respective performance under almost perfect conditions. We then study real languages, namely Latin, Italian and Spanish, to see if those performances generalise well. We show that both model types manage to learn sound changes despite data scarcity, although the best performing model type depends on several parameters such as the size of the training data, the ambiguity, and the prediction direction.</abstract>
    <identifier type="citekey">fourrier-sagot-2020-comparing</identifier>
    <location>
        <url>https://aclanthology.org/2020.lt4hala-1.12</url>
    </location>
    <part>
        <date>2020-05</date>
        <extent unit="page">
            <start>79</start>
            <end>83</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Comparing Statistical and Neural Models for Learning Sound Correspondences
%A Fourrier, Clémentine
%A Sagot, Benoît
%Y Sprugnoli, Rachele
%Y Passarotti, Marco
%S Proceedings of LT4HALA 2020 - 1st Workshop on Language Technologies for Historical and Ancient Languages
%D 2020
%8 May
%I European Language Resources Association (ELRA)
%C Marseille, France
%@ 979-10-95546-53-5
%G English
%F fourrier-sagot-2020-comparing
%X Cognate prediction and proto-form reconstruction are key tasks in computational historical linguistics that rely on the study of sound change regularity. Solving these tasks appears to be very similar to machine translation, though methods from that field have barely been applied to historical linguistics. Therefore, in this paper, we investigate the learnability of sound correspondences between a proto-language and daughter languages for two machine-translation-inspired models, one statistical, the other neural. We first carry out our experiments on plausible artificial languages, without noise, in order to study the role of each parameter on the algorithms respective performance under almost perfect conditions. We then study real languages, namely Latin, Italian and Spanish, to see if those performances generalise well. We show that both model types manage to learn sound changes despite data scarcity, although the best performing model type depends on several parameters such as the size of the training data, the ambiguity, and the prediction direction.
%U https://aclanthology.org/2020.lt4hala-1.12
%P 79-83

Markdown (Informal)

[Comparing Statistical and Neural Models for Learning Sound Correspondences](https://aclanthology.org/2020.lt4hala-1.12) (Fourrier & Sagot, LT4HALA 2020)

• Comparing Statistical and Neural Models for Learning Sound Correspondences (Fourrier & Sagot, LT4HALA 2020)

ACL

• Clémentine Fourrier and Benoît Sagot. 2020. Comparing Statistical and Neural Models for Learning Sound Correspondences. In Proceedings of LT4HALA 2020 - 1st Workshop on Language Technologies for Historical and Ancient Languages, pages 79–83, Marseille, France. European Language Resources Association (ELRA).