@inproceedings{wu-etal-2019-language,
title = "Language Discrimination and Transfer Learning for Similar Languages: Experiments with Feature Combinations and Adaptation",
author = {Wu, Nianheng and
DeMattos, Eric and
So, Kwok Him and
Chen, Pin-zhen and
{\c{C}}{\"o}ltekin, {\c{C}}a{\u{g}}r{\i}},
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/W19-1406",
doi = "10.18653/v1/W19-1406",
pages = "54--63",
abstract = "This paper describes the work done by team tearsofjoy participating in the VarDial 2019 Evaluation Campaign. We developed two systems based on Support Vector Machines: SVM with a flat combination of features and SVM ensembles. We participated in all language/dialect identification tasks, as well as the Moldavian vs. Romanian cross-dialect topic identification (MRC) task. Our team achieved first place in German Dialect identification (GDI) and MRC subtasks 2 and 3, second place in the simplified variant of Discriminating between Mainland and Taiwan variation of Mandarin Chinese (DMT) as well as Cuneiform Language Identification (CLI), and third and fifth place in DMT traditional and MRC subtask 1 respectively. In most cases, the SVM with a flat combination of features performed better than SVM ensembles. Besides describing the systems and the results obtained by them, we provide a tentative comparison between the feature combination methods, and present additional experiments with a method of adaptation to the test set, which may indicate potential pitfalls with some of the data sets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2019-language">
<titleInfo>
<title>Language Discrimination and Transfer Learning for Similar Languages: Experiments with Feature Combinations and Adaptation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nianheng</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">DeMattos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kwok</namePart>
<namePart type="given">Him</namePart>
<namePart type="family">So</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pin-zhen</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Çağrı</namePart>
<namePart type="family">Çöltekin</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>This paper describes the work done by team tearsofjoy participating in the VarDial 2019 Evaluation Campaign. We developed two systems based on Support Vector Machines: SVM with a flat combination of features and SVM ensembles. We participated in all language/dialect identification tasks, as well as the Moldavian vs. Romanian cross-dialect topic identification (MRC) task. Our team achieved first place in German Dialect identification (GDI) and MRC subtasks 2 and 3, second place in the simplified variant of Discriminating between Mainland and Taiwan variation of Mandarin Chinese (DMT) as well as Cuneiform Language Identification (CLI), and third and fifth place in DMT traditional and MRC subtask 1 respectively. In most cases, the SVM with a flat combination of features performed better than SVM ensembles. Besides describing the systems and the results obtained by them, we provide a tentative comparison between the feature combination methods, and present additional experiments with a method of adaptation to the test set, which may indicate potential pitfalls with some of the data sets.</abstract>
<identifier type="citekey">wu-etal-2019-language</identifier>
<identifier type="doi">10.18653/v1/W19-1406</identifier>
<location>
<url>https://aclanthology.org/W19-1406</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>54</start>
<end>63</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Language Discrimination and Transfer Learning for Similar Languages: Experiments with Feature Combinations and Adaptation
%A Wu, Nianheng
%A DeMattos, Eric
%A So, Kwok Him
%A Chen, Pin-zhen
%A Çöltekin, Çağrı
%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 wu-etal-2019-language
%X This paper describes the work done by team tearsofjoy participating in the VarDial 2019 Evaluation Campaign. We developed two systems based on Support Vector Machines: SVM with a flat combination of features and SVM ensembles. We participated in all language/dialect identification tasks, as well as the Moldavian vs. Romanian cross-dialect topic identification (MRC) task. Our team achieved first place in German Dialect identification (GDI) and MRC subtasks 2 and 3, second place in the simplified variant of Discriminating between Mainland and Taiwan variation of Mandarin Chinese (DMT) as well as Cuneiform Language Identification (CLI), and third and fifth place in DMT traditional and MRC subtask 1 respectively. In most cases, the SVM with a flat combination of features performed better than SVM ensembles. Besides describing the systems and the results obtained by them, we provide a tentative comparison between the feature combination methods, and present additional experiments with a method of adaptation to the test set, which may indicate potential pitfalls with some of the data sets.
%R 10.18653/v1/W19-1406
%U https://aclanthology.org/W19-1406
%U https://doi.org/10.18653/v1/W19-1406
%P 54-63
Markdown (Informal)
[Language Discrimination and Transfer Learning for Similar Languages: Experiments with Feature Combinations and Adaptation](https://aclanthology.org/W19-1406) (Wu et al., VarDial 2019)
ACL