@inproceedings{yang-xiang-2019-naive,
title = "Naive {B}ayes and {B}i{LSTM} Ensemble for Discriminating between Mainland and {T}aiwan Variation of {M}andarin {C}hinese",
author = "Yang, Li and
Xiang, Yang",
editor = {Zampieri, Marcos and
Nakov, Preslav and
Malmasi, Shervin and
Ljube{\v{s}}i{\'c}, Nikola and
Tiedemann, J{\"o}rg and
Ali, Ahmed},
booktitle = "Proceedings of the Sixth Workshop on {NLP} for Similar Languages, Varieties and Dialects",
month = jun,
year = "2019",
address = "Ann Arbor, Michigan",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-1412",
doi = "10.18653/v1/W19-1412",
pages = "120--127",
abstract = "Automatic dialect identification is a more challengingctask than language identification, as it requires the ability to discriminate between varieties of one language. In this paper, we propose an ensemble based system, which combines traditional machine learning models trained on bag of n-gram fetures, with deep learning models trained on word embeddings, to solve the Discriminating between Mainland and Taiwan Variation of Mandarin Chinese (DMT) shared task at VarDial 2019. Our experiments show that a character bigram-trigram combination based Naive Bayes is a very strong model for identifying varieties of Mandarin Chinense. Through further ensemble of Navie Bayes and BiLSTM, our system (team: itsalexyang) achived an macro-averaged F1 score of 0.8530 and 0.8687 in two tracks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-xiang-2019-naive">
<titleInfo>
<title>Naive Bayes and BiLSTM Ensemble for Discriminating between Mainland and Taiwan Variation of Mandarin Chinese</title>
</titleInfo>
<name type="personal">
<namePart type="given">Li</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Xiang</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 Sixth Workshop on NLP for Similar Languages, Varieties and Dialects</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shervin</namePart>
<namePart type="family">Malmasi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikola</namePart>
<namePart type="family">Ljubešić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jörg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Ali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Ann Arbor, Michigan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automatic dialect identification is a more challengingctask than language identification, as it requires the ability to discriminate between varieties of one language. In this paper, we propose an ensemble based system, which combines traditional machine learning models trained on bag of n-gram fetures, with deep learning models trained on word embeddings, to solve the Discriminating between Mainland and Taiwan Variation of Mandarin Chinese (DMT) shared task at VarDial 2019. Our experiments show that a character bigram-trigram combination based Naive Bayes is a very strong model for identifying varieties of Mandarin Chinense. Through further ensemble of Navie Bayes and BiLSTM, our system (team: itsalexyang) achived an macro-averaged F1 score of 0.8530 and 0.8687 in two tracks.</abstract>
<identifier type="citekey">yang-xiang-2019-naive</identifier>
<identifier type="doi">10.18653/v1/W19-1412</identifier>
<location>
<url>https://aclanthology.org/W19-1412</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>120</start>
<end>127</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Naive Bayes and BiLSTM Ensemble for Discriminating between Mainland and Taiwan Variation of Mandarin Chinese
%A Yang, Li
%A Xiang, Yang
%Y Zampieri, Marcos
%Y Nakov, Preslav
%Y Malmasi, Shervin
%Y Ljubešić, Nikola
%Y Tiedemann, Jörg
%Y Ali, Ahmed
%S Proceedings of the Sixth Workshop on NLP for Similar Languages, Varieties and Dialects
%D 2019
%8 June
%I Association for Computational Linguistics
%C Ann Arbor, Michigan
%F yang-xiang-2019-naive
%X Automatic dialect identification is a more challengingctask than language identification, as it requires the ability to discriminate between varieties of one language. In this paper, we propose an ensemble based system, which combines traditional machine learning models trained on bag of n-gram fetures, with deep learning models trained on word embeddings, to solve the Discriminating between Mainland and Taiwan Variation of Mandarin Chinese (DMT) shared task at VarDial 2019. Our experiments show that a character bigram-trigram combination based Naive Bayes is a very strong model for identifying varieties of Mandarin Chinense. Through further ensemble of Navie Bayes and BiLSTM, our system (team: itsalexyang) achived an macro-averaged F1 score of 0.8530 and 0.8687 in two tracks.
%R 10.18653/v1/W19-1412
%U https://aclanthology.org/W19-1412
%U https://doi.org/10.18653/v1/W19-1412
%P 120-127
Markdown (Informal)
[Naive Bayes and BiLSTM Ensemble for Discriminating between Mainland and Taiwan Variation of Mandarin Chinese](https://aclanthology.org/W19-1412) (Yang & Xiang, VarDial 2019)
ACL