@article{borschinger-johnson-2014-exploring,
title = "Exploring the Role of Stress in {B}ayesian Word Segmentation using {A}daptor {G}rammars",
author = {B{\"o}rschinger, Benjamin and
Johnson, Mark},
editor = "Lin, Dekang and
Collins, Michael and
Lee, Lillian",
journal = "Transactions of the Association for Computational Linguistics",
volume = "2",
year = "2014",
address = "Cambridge, MA",
publisher = "MIT Press",
url = "https://aclanthology.org/Q14-1008",
doi = "10.1162/tacl_a_00168",
pages = "93--104",
abstract = "Stress has long been established as a major cue in word segmentation for English infants. We show that enabling a current state-of-the-art Bayesian word segmentation model to take advantage of stress cues noticeably improves its performance. We find that the improvements range from 10 to 4{\%}, depending on both the use of phonotactic cues and, to a lesser extent, the amount of evidence available to the learner. We also find that in particular early on, stress cues are much more useful for our model than phonotactic cues by themselves, consistent with the finding that children do seem to use stress cues before they use phonotactic cues. Finally, we study how the model{'}s knowledge about stress patterns evolves over time. We not only find that our model correctly acquires the most frequent patterns relatively quickly but also that the Unique Stress Constraint that is at the heart of a previously proposed model does not need to be built in but can be acquired jointly with word segmentation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="borschinger-johnson-2014-exploring">
<titleInfo>
<title>Exploring the Role of Stress in Bayesian Word Segmentation using Adaptor Grammars</title>
</titleInfo>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="family">Börschinger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Johnson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<genre authority="bibutilsgt">journal article</genre>
<relatedItem type="host">
<titleInfo>
<title>Transactions of the Association for Computational Linguistics</title>
</titleInfo>
<originInfo>
<issuance>continuing</issuance>
<publisher>MIT Press</publisher>
<place>
<placeTerm type="text">Cambridge, MA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">periodical</genre>
<genre authority="bibutilsgt">academic journal</genre>
</relatedItem>
<abstract>Stress has long been established as a major cue in word segmentation for English infants. We show that enabling a current state-of-the-art Bayesian word segmentation model to take advantage of stress cues noticeably improves its performance. We find that the improvements range from 10 to 4%, depending on both the use of phonotactic cues and, to a lesser extent, the amount of evidence available to the learner. We also find that in particular early on, stress cues are much more useful for our model than phonotactic cues by themselves, consistent with the finding that children do seem to use stress cues before they use phonotactic cues. Finally, we study how the model’s knowledge about stress patterns evolves over time. We not only find that our model correctly acquires the most frequent patterns relatively quickly but also that the Unique Stress Constraint that is at the heart of a previously proposed model does not need to be built in but can be acquired jointly with word segmentation.</abstract>
<identifier type="citekey">borschinger-johnson-2014-exploring</identifier>
<identifier type="doi">10.1162/tacl_a_00168</identifier>
<location>
<url>https://aclanthology.org/Q14-1008</url>
</location>
<part>
<date>2014</date>
<detail type="volume"><number>2</number></detail>
<extent unit="page">
<start>93</start>
<end>104</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T Exploring the Role of Stress in Bayesian Word Segmentation using Adaptor Grammars
%A Börschinger, Benjamin
%A Johnson, Mark
%J Transactions of the Association for Computational Linguistics
%D 2014
%V 2
%I MIT Press
%C Cambridge, MA
%F borschinger-johnson-2014-exploring
%X Stress has long been established as a major cue in word segmentation for English infants. We show that enabling a current state-of-the-art Bayesian word segmentation model to take advantage of stress cues noticeably improves its performance. We find that the improvements range from 10 to 4%, depending on both the use of phonotactic cues and, to a lesser extent, the amount of evidence available to the learner. We also find that in particular early on, stress cues are much more useful for our model than phonotactic cues by themselves, consistent with the finding that children do seem to use stress cues before they use phonotactic cues. Finally, we study how the model’s knowledge about stress patterns evolves over time. We not only find that our model correctly acquires the most frequent patterns relatively quickly but also that the Unique Stress Constraint that is at the heart of a previously proposed model does not need to be built in but can be acquired jointly with word segmentation.
%R 10.1162/tacl_a_00168
%U https://aclanthology.org/Q14-1008
%U https://doi.org/10.1162/tacl_a_00168
%P 93-104
Markdown (Informal)
[Exploring the Role of Stress in Bayesian Word Segmentation using Adaptor Grammars](https://aclanthology.org/Q14-1008) (Börschinger & Johnson, TACL 2014)
ACL