@inproceedings{sung-etal-2024-new,
title = "A New Dataset for Tonal and Segmental Dialectometry from the {Y}ue- and Pinghua-Speaking Area",
author = "Sung, Ho Wang Matthew and
Prokic, Jelena and
Chen, Yiya",
editor = "Hahn, Michael and
Sorokin, Alexey and
Kumar, Ritesh and
Shcherbakov, Andreas and
Otmakhova, Yulia and
Yang, Jinrui and
Serikov, Oleg and
Rani, Priya and
Ponti, Edoardo M. and
Murado{\u{g}}lu, Saliha and
Gao, Rena and
Cotterell, Ryan and
Vylomova, Ekaterina",
booktitle = "Proceedings of the 6th Workshop on Research in Computational Linguistic Typology and Multilingual NLP",
month = mar,
year = "2024",
address = "St. Julian's, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.sigtyp-1.3/",
pages = "25--36",
abstract = "Traditional dialectology or dialect geography is the study of geographical variation of language. Originated in Europe and pioneered in Germany and France, this field has predominantly been focusing on sounds, more specifically, on segments. Similarly, quantitative approaches to language variation concerned with the phonetic level are in most cases focusing on segments as well. However, more than half of the world`s languages include lexical tones (Yip, 2002). Despite this, tones are still underexplored in quantitative language comparison, partly due to the low accessibility of the suitable data. This paper aims to introduce a newly digitised dataset which comes from the Yue- and Pinghua-speaking areas in Southern China, with over 100 dialects. This dataset consists of two parts: tones and segments. In this paper, we illustrate how we can computationaly model tones in order to explore linguistic variation. We have applied a tone distance metric on our data, and we have found that 1) dialects also form a continuum on the tonal level and 2) other than tonemic (inventory) and tonetic differences, dialects can also differ in the lexical distribution of tones. The availability of this dataset will hopefully enable further exploration of the role of tones in quantitative typology and NLP research."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sung-etal-2024-new">
<titleInfo>
<title>A New Dataset for Tonal and Segmental Dialectometry from the Yue- and Pinghua-Speaking Area</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ho</namePart>
<namePart type="given">Wang</namePart>
<namePart type="given">Matthew</namePart>
<namePart type="family">Sung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jelena</namePart>
<namePart type="family">Prokic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiya</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 6th Workshop on Research in Computational Linguistic Typology and Multilingual NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Hahn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexey</namePart>
<namePart type="family">Sorokin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Shcherbakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulia</namePart>
<namePart type="family">Otmakhova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinrui</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oleg</namePart>
<namePart type="family">Serikov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Priya</namePart>
<namePart type="family">Rani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Edoardo</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Ponti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saliha</namePart>
<namePart type="family">Muradoğlu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rena</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Vylomova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julian’s, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Traditional dialectology or dialect geography is the study of geographical variation of language. Originated in Europe and pioneered in Germany and France, this field has predominantly been focusing on sounds, more specifically, on segments. Similarly, quantitative approaches to language variation concerned with the phonetic level are in most cases focusing on segments as well. However, more than half of the world‘s languages include lexical tones (Yip, 2002). Despite this, tones are still underexplored in quantitative language comparison, partly due to the low accessibility of the suitable data. This paper aims to introduce a newly digitised dataset which comes from the Yue- and Pinghua-speaking areas in Southern China, with over 100 dialects. This dataset consists of two parts: tones and segments. In this paper, we illustrate how we can computationaly model tones in order to explore linguistic variation. We have applied a tone distance metric on our data, and we have found that 1) dialects also form a continuum on the tonal level and 2) other than tonemic (inventory) and tonetic differences, dialects can also differ in the lexical distribution of tones. The availability of this dataset will hopefully enable further exploration of the role of tones in quantitative typology and NLP research.</abstract>
<identifier type="citekey">sung-etal-2024-new</identifier>
<location>
<url>https://aclanthology.org/2024.sigtyp-1.3/</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>25</start>
<end>36</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A New Dataset for Tonal and Segmental Dialectometry from the Yue- and Pinghua-Speaking Area
%A Sung, Ho Wang Matthew
%A Prokic, Jelena
%A Chen, Yiya
%Y Hahn, Michael
%Y Sorokin, Alexey
%Y Kumar, Ritesh
%Y Shcherbakov, Andreas
%Y Otmakhova, Yulia
%Y Yang, Jinrui
%Y Serikov, Oleg
%Y Rani, Priya
%Y Ponti, Edoardo M.
%Y Muradoğlu, Saliha
%Y Gao, Rena
%Y Cotterell, Ryan
%Y Vylomova, Ekaterina
%S Proceedings of the 6th Workshop on Research in Computational Linguistic Typology and Multilingual NLP
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F sung-etal-2024-new
%X Traditional dialectology or dialect geography is the study of geographical variation of language. Originated in Europe and pioneered in Germany and France, this field has predominantly been focusing on sounds, more specifically, on segments. Similarly, quantitative approaches to language variation concerned with the phonetic level are in most cases focusing on segments as well. However, more than half of the world‘s languages include lexical tones (Yip, 2002). Despite this, tones are still underexplored in quantitative language comparison, partly due to the low accessibility of the suitable data. This paper aims to introduce a newly digitised dataset which comes from the Yue- and Pinghua-speaking areas in Southern China, with over 100 dialects. This dataset consists of two parts: tones and segments. In this paper, we illustrate how we can computationaly model tones in order to explore linguistic variation. We have applied a tone distance metric on our data, and we have found that 1) dialects also form a continuum on the tonal level and 2) other than tonemic (inventory) and tonetic differences, dialects can also differ in the lexical distribution of tones. The availability of this dataset will hopefully enable further exploration of the role of tones in quantitative typology and NLP research.
%U https://aclanthology.org/2024.sigtyp-1.3/
%P 25-36
Markdown (Informal)
[A New Dataset for Tonal and Segmental Dialectometry from the Yue- and Pinghua-Speaking Area](https://aclanthology.org/2024.sigtyp-1.3/) (Sung et al., SIGTYP 2024)
ACL