@inproceedings{chu-etal-2020-learning,
title = "{L}earning to {P}ronounce {C}hinese {W}ithout a {P}ronunciation {D}ictionary",
author = "Chu, Christopher and
Fang, Scot and
Knight, Kevin",
editor = "Webber, Bonnie and
Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.458",
doi = "10.18653/v1/2020.emnlp-main.458",
pages = "5687--5693",
abstract = "We demonstrate a program that learns to pronounce Chinese text in Mandarin, without a pronunciation dictionary. From non-parallel streams of Chinese characters and Chinese pinyin syllables, it establishes a many-to-many mapping between characters and pronunciations. Using unsupervised methods, the program effectively deciphers writing into speech. Its token-level character-to-syllable accuracy is 89{\%}, which significantly exceeds the 22{\%} accuracy of prior work.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chu-etal-2020-learning">
<titleInfo>
<title>Learning to Pronounce Chinese Without a Pronunciation Dictionary</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Chu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scot</namePart>
<namePart type="family">Fang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Knight</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Webber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We demonstrate a program that learns to pronounce Chinese text in Mandarin, without a pronunciation dictionary. From non-parallel streams of Chinese characters and Chinese pinyin syllables, it establishes a many-to-many mapping between characters and pronunciations. Using unsupervised methods, the program effectively deciphers writing into speech. Its token-level character-to-syllable accuracy is 89%, which significantly exceeds the 22% accuracy of prior work.</abstract>
<identifier type="citekey">chu-etal-2020-learning</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.458</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.458</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>5687</start>
<end>5693</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning to Pronounce Chinese Without a Pronunciation Dictionary
%A Chu, Christopher
%A Fang, Scot
%A Knight, Kevin
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F chu-etal-2020-learning
%X We demonstrate a program that learns to pronounce Chinese text in Mandarin, without a pronunciation dictionary. From non-parallel streams of Chinese characters and Chinese pinyin syllables, it establishes a many-to-many mapping between characters and pronunciations. Using unsupervised methods, the program effectively deciphers writing into speech. Its token-level character-to-syllable accuracy is 89%, which significantly exceeds the 22% accuracy of prior work.
%R 10.18653/v1/2020.emnlp-main.458
%U https://aclanthology.org/2020.emnlp-main.458
%U https://doi.org/10.18653/v1/2020.emnlp-main.458
%P 5687-5693
Markdown (Informal)
[Learning to Pronounce Chinese Without a Pronunciation Dictionary](https://aclanthology.org/2020.emnlp-main.458) (Chu et al., EMNLP 2020)
ACL