@inproceedings{kolachina-magyar-2019-phone,
title = "What do phone embeddings learn about Phonology?",
author = "Kolachina, Sudheer and
Magyar, Lilla",
editor = "Nicolai, Garrett and
Cotterell, Ryan",
booktitle = "Proceedings of the 16th Workshop on Computational Research in Phonetics, Phonology, and Morphology",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-4219",
doi = "10.18653/v1/W19-4219",
pages = "160--169",
abstract = "Recent work has looked at evaluation of phone embeddings using sound analogies and correlations between distinctive feature space and embedding space. It has not been clear what aspects of natural language phonology are learnt by neural network inspired distributed representational models such as word2vec. To study the kinds of phonological relationships learnt by phone embeddings, we present artificial phonology experiments that show that phone embeddings learn paradigmatic relationships such as phonemic and allophonic distribution quite well. They are also able to capture co-occurrence restrictions among vowels such as those observed in languages with vowel harmony. However, they are unable to learn co-occurrence restrictions among the class of consonants.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kolachina-magyar-2019-phone">
<titleInfo>
<title>What do phone embeddings learn about Phonology?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sudheer</namePart>
<namePart type="family">Kolachina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lilla</namePart>
<namePart type="family">Magyar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th Workshop on Computational Research in Phonetics, Phonology, and Morphology</title>
</titleInfo>
<name type="personal">
<namePart type="given">Garrett</namePart>
<namePart type="family">Nicolai</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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent work has looked at evaluation of phone embeddings using sound analogies and correlations between distinctive feature space and embedding space. It has not been clear what aspects of natural language phonology are learnt by neural network inspired distributed representational models such as word2vec. To study the kinds of phonological relationships learnt by phone embeddings, we present artificial phonology experiments that show that phone embeddings learn paradigmatic relationships such as phonemic and allophonic distribution quite well. They are also able to capture co-occurrence restrictions among vowels such as those observed in languages with vowel harmony. However, they are unable to learn co-occurrence restrictions among the class of consonants.</abstract>
<identifier type="citekey">kolachina-magyar-2019-phone</identifier>
<identifier type="doi">10.18653/v1/W19-4219</identifier>
<location>
<url>https://aclanthology.org/W19-4219</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>160</start>
<end>169</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T What do phone embeddings learn about Phonology?
%A Kolachina, Sudheer
%A Magyar, Lilla
%Y Nicolai, Garrett
%Y Cotterell, Ryan
%S Proceedings of the 16th Workshop on Computational Research in Phonetics, Phonology, and Morphology
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence, Italy
%F kolachina-magyar-2019-phone
%X Recent work has looked at evaluation of phone embeddings using sound analogies and correlations between distinctive feature space and embedding space. It has not been clear what aspects of natural language phonology are learnt by neural network inspired distributed representational models such as word2vec. To study the kinds of phonological relationships learnt by phone embeddings, we present artificial phonology experiments that show that phone embeddings learn paradigmatic relationships such as phonemic and allophonic distribution quite well. They are also able to capture co-occurrence restrictions among vowels such as those observed in languages with vowel harmony. However, they are unable to learn co-occurrence restrictions among the class of consonants.
%R 10.18653/v1/W19-4219
%U https://aclanthology.org/W19-4219
%U https://doi.org/10.18653/v1/W19-4219
%P 160-169
Markdown (Informal)
[What do phone embeddings learn about Phonology?](https://aclanthology.org/W19-4219) (Kolachina & Magyar, ACL 2019)
ACL
- Sudheer Kolachina and Lilla Magyar. 2019. What do phone embeddings learn about Phonology?. In Proceedings of the 16th Workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 160–169, Florence, Italy. Association for Computational Linguistics.