@inproceedings{feliciano-de-faria-2019-role,
title = "The Role of Utterance Boundaries and Word Frequencies for Part-of-speech Learning in {B}razilian {P}ortuguese Through Distributional Analysis",
author = "Feliciano de Faria, Pablo Picasso",
editor = "Chersoni, Emmanuele and
Jacobs, Cassandra and
Lenci, Alessandro and
Linzen, Tal and
Pr{\'e}vot, Laurent and
Santus, Enrico",
booktitle = "Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-2917",
doi = "10.18653/v1/W19-2917",
pages = "152--159",
abstract = "In this study, we address the problem of part-of-speech (or syntactic category) learning during language acquisition through distributional analysis of utterances. A model based on Redington et al.{'}s (1998) distributional learner is used to investigate the informativeness of distributional information in Brazilian Portuguese (BP). The data provided to the learner comes from two publicly available corpora of child directed speech. We present preliminary results from two experiments. The first one investigates the effects of different assumptions about utterance boundaries when presenting the input data to the learner. The second experiment compares the learner{'}s performance when counting contextual words{'} frequencies versus just acknowledging their co-occurrence with a given target word. In general, our results indicate that explicit boundaries are more informative, frequencies are important, and that distributional information is useful to the child as a source of categorial information. These results are in accordance with Redington et al.{'}s findings for English.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="feliciano-de-faria-2019-role">
<titleInfo>
<title>The Role of Utterance Boundaries and Word Frequencies for Part-of-speech Learning in Brazilian Portuguese Through Distributional Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pablo</namePart>
<namePart type="given">Picasso</namePart>
<namePart type="family">Feliciano de Faria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Emmanuele</namePart>
<namePart type="family">Chersoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cassandra</namePart>
<namePart type="family">Jacobs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tal</namePart>
<namePart type="family">Linzen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laurent</namePart>
<namePart type="family">Prévot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this study, we address the problem of part-of-speech (or syntactic category) learning during language acquisition through distributional analysis of utterances. A model based on Redington et al.’s (1998) distributional learner is used to investigate the informativeness of distributional information in Brazilian Portuguese (BP). The data provided to the learner comes from two publicly available corpora of child directed speech. We present preliminary results from two experiments. The first one investigates the effects of different assumptions about utterance boundaries when presenting the input data to the learner. The second experiment compares the learner’s performance when counting contextual words’ frequencies versus just acknowledging their co-occurrence with a given target word. In general, our results indicate that explicit boundaries are more informative, frequencies are important, and that distributional information is useful to the child as a source of categorial information. These results are in accordance with Redington et al.’s findings for English.</abstract>
<identifier type="citekey">feliciano-de-faria-2019-role</identifier>
<identifier type="doi">10.18653/v1/W19-2917</identifier>
<location>
<url>https://aclanthology.org/W19-2917</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>152</start>
<end>159</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Role of Utterance Boundaries and Word Frequencies for Part-of-speech Learning in Brazilian Portuguese Through Distributional Analysis
%A Feliciano de Faria, Pablo Picasso
%Y Chersoni, Emmanuele
%Y Jacobs, Cassandra
%Y Lenci, Alessandro
%Y Linzen, Tal
%Y Prévot, Laurent
%Y Santus, Enrico
%S Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F feliciano-de-faria-2019-role
%X In this study, we address the problem of part-of-speech (or syntactic category) learning during language acquisition through distributional analysis of utterances. A model based on Redington et al.’s (1998) distributional learner is used to investigate the informativeness of distributional information in Brazilian Portuguese (BP). The data provided to the learner comes from two publicly available corpora of child directed speech. We present preliminary results from two experiments. The first one investigates the effects of different assumptions about utterance boundaries when presenting the input data to the learner. The second experiment compares the learner’s performance when counting contextual words’ frequencies versus just acknowledging their co-occurrence with a given target word. In general, our results indicate that explicit boundaries are more informative, frequencies are important, and that distributional information is useful to the child as a source of categorial information. These results are in accordance with Redington et al.’s findings for English.
%R 10.18653/v1/W19-2917
%U https://aclanthology.org/W19-2917
%U https://doi.org/10.18653/v1/W19-2917
%P 152-159
Markdown (Informal)
[The Role of Utterance Boundaries and Word Frequencies for Part-of-speech Learning in Brazilian Portuguese Through Distributional Analysis](https://aclanthology.org/W19-2917) (Feliciano de Faria, CMCL 2019)
ACL