@inproceedings{sato-etal-2022-building,
title = "Building Large-Scale {J}apanese Pronunciation-Annotated Corpora for Reading Heteronymous Logograms",
author = "Sato, Fumikazu and
Yoshinaga, Naoki and
Kitsuregawa, Masaru",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.770",
pages = "7113--7121",
abstract = "Although screen readers enable visually impaired people to read written text via speech, the ambiguities in pronunciations of heteronyms cause wrong reading, which has a serious impact on the text understanding. Especially in Japanese, there are many common heteronyms expressed by logograms (Chinese characters or kanji) that have totally different pronunciations (and meanings). In this study, to improve the accuracy of pronunciation prediction, we construct two large-scale Japanese corpora that annotate kanji characters with their pronunciations. Using existing language resources on i) book titles compiled by the National Diet Library and ii) the books in a Japanese digital library called Aozora Bunko and their Braille translations, we develop two large-scale pronunciation-annotated corpora for training pronunciation prediction models. We first extract sentence-level alignments between the Aozora Bunko text and its pronunciation converted from the Braille data. We then perform dictionary-based pattern matching based on morphological dictionaries to find word-level pronunciation alignments. We have ultimately obtained the Book Title corpus with 336M characters (16.4M book titles) and the Aozora Bunko corpus with 52M characters (1.6M sentences). We analyzed pronunciation distributions for 203 common heteronyms, and trained a BERT-based pronunciation prediction model for 93 heteronyms, which achieved an average accuracy of 0.939.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sato-etal-2022-building">
<titleInfo>
<title>Building Large-Scale Japanese Pronunciation-Annotated Corpora for Reading Heteronymous Logograms</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fumikazu</namePart>
<namePart type="family">Sato</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoki</namePart>
<namePart type="family">Yoshinaga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masaru</namePart>
<namePart type="family">Kitsuregawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Although screen readers enable visually impaired people to read written text via speech, the ambiguities in pronunciations of heteronyms cause wrong reading, which has a serious impact on the text understanding. Especially in Japanese, there are many common heteronyms expressed by logograms (Chinese characters or kanji) that have totally different pronunciations (and meanings). In this study, to improve the accuracy of pronunciation prediction, we construct two large-scale Japanese corpora that annotate kanji characters with their pronunciations. Using existing language resources on i) book titles compiled by the National Diet Library and ii) the books in a Japanese digital library called Aozora Bunko and their Braille translations, we develop two large-scale pronunciation-annotated corpora for training pronunciation prediction models. We first extract sentence-level alignments between the Aozora Bunko text and its pronunciation converted from the Braille data. We then perform dictionary-based pattern matching based on morphological dictionaries to find word-level pronunciation alignments. We have ultimately obtained the Book Title corpus with 336M characters (16.4M book titles) and the Aozora Bunko corpus with 52M characters (1.6M sentences). We analyzed pronunciation distributions for 203 common heteronyms, and trained a BERT-based pronunciation prediction model for 93 heteronyms, which achieved an average accuracy of 0.939.</abstract>
<identifier type="citekey">sato-etal-2022-building</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.770</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>7113</start>
<end>7121</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Building Large-Scale Japanese Pronunciation-Annotated Corpora for Reading Heteronymous Logograms
%A Sato, Fumikazu
%A Yoshinaga, Naoki
%A Kitsuregawa, Masaru
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F sato-etal-2022-building
%X Although screen readers enable visually impaired people to read written text via speech, the ambiguities in pronunciations of heteronyms cause wrong reading, which has a serious impact on the text understanding. Especially in Japanese, there are many common heteronyms expressed by logograms (Chinese characters or kanji) that have totally different pronunciations (and meanings). In this study, to improve the accuracy of pronunciation prediction, we construct two large-scale Japanese corpora that annotate kanji characters with their pronunciations. Using existing language resources on i) book titles compiled by the National Diet Library and ii) the books in a Japanese digital library called Aozora Bunko and their Braille translations, we develop two large-scale pronunciation-annotated corpora for training pronunciation prediction models. We first extract sentence-level alignments between the Aozora Bunko text and its pronunciation converted from the Braille data. We then perform dictionary-based pattern matching based on morphological dictionaries to find word-level pronunciation alignments. We have ultimately obtained the Book Title corpus with 336M characters (16.4M book titles) and the Aozora Bunko corpus with 52M characters (1.6M sentences). We analyzed pronunciation distributions for 203 common heteronyms, and trained a BERT-based pronunciation prediction model for 93 heteronyms, which achieved an average accuracy of 0.939.
%U https://aclanthology.org/2022.lrec-1.770
%P 7113-7121
Markdown (Informal)
[Building Large-Scale Japanese Pronunciation-Annotated Corpora for Reading Heteronymous Logograms](https://aclanthology.org/2022.lrec-1.770) (Sato et al., LREC 2022)
ACL