@inproceedings{mirea-bicknell-2019-using,
title = "Using {LSTM}s to Assess the Obligatoriness of Phonological Distinctive Features for Phonotactic Learning",
author = "Mirea, Nicole and
Bicknell, Klinton",
editor = "Korhonen, Anna and
Traum, David and
M{\`a}rquez, Llu{\'i}s",
booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P19-1155/",
doi = "10.18653/v1/P19-1155",
pages = "1595--1605",
abstract = "To ascertain the importance of phonetic information in the form of phonological distinctive features for the purpose of segment-level phonotactic acquisition, we compare the performance of two recurrent neural network models of phonotactic learning: one that has access to distinctive features at the start of the learning process, and one that does not. Though the predictions of both models are significantly correlated with human judgments of non-words, the feature-naive model significantly outperforms the feature-aware one in terms of probability assigned to a held-out test set of English words, suggesting that distinctive features are not obligatory for learning phonotactic patterns at the segment level."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mirea-bicknell-2019-using">
<titleInfo>
<title>Using LSTMs to Assess the Obligatoriness of Phonological Distinctive Features for Phonotactic Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicole</namePart>
<namePart type="family">Mirea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Klinton</namePart>
<namePart type="family">Bicknell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Korhonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Traum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Màrquez</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>To ascertain the importance of phonetic information in the form of phonological distinctive features for the purpose of segment-level phonotactic acquisition, we compare the performance of two recurrent neural network models of phonotactic learning: one that has access to distinctive features at the start of the learning process, and one that does not. Though the predictions of both models are significantly correlated with human judgments of non-words, the feature-naive model significantly outperforms the feature-aware one in terms of probability assigned to a held-out test set of English words, suggesting that distinctive features are not obligatory for learning phonotactic patterns at the segment level.</abstract>
<identifier type="citekey">mirea-bicknell-2019-using</identifier>
<identifier type="doi">10.18653/v1/P19-1155</identifier>
<location>
<url>https://aclanthology.org/P19-1155/</url>
</location>
<part>
<date>2019-07</date>
<extent unit="page">
<start>1595</start>
<end>1605</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Using LSTMs to Assess the Obligatoriness of Phonological Distinctive Features for Phonotactic Learning
%A Mirea, Nicole
%A Bicknell, Klinton
%Y Korhonen, Anna
%Y Traum, David
%Y Màrquez, Lluís
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019
%8 July
%I Association for Computational Linguistics
%C Florence, Italy
%F mirea-bicknell-2019-using
%X To ascertain the importance of phonetic information in the form of phonological distinctive features for the purpose of segment-level phonotactic acquisition, we compare the performance of two recurrent neural network models of phonotactic learning: one that has access to distinctive features at the start of the learning process, and one that does not. Though the predictions of both models are significantly correlated with human judgments of non-words, the feature-naive model significantly outperforms the feature-aware one in terms of probability assigned to a held-out test set of English words, suggesting that distinctive features are not obligatory for learning phonotactic patterns at the segment level.
%R 10.18653/v1/P19-1155
%U https://aclanthology.org/P19-1155/
%U https://doi.org/10.18653/v1/P19-1155
%P 1595-1605
Markdown (Informal)
[Using LSTMs to Assess the Obligatoriness of Phonological Distinctive Features for Phonotactic Learning](https://aclanthology.org/P19-1155/) (Mirea & Bicknell, ACL 2019)
ACL