@inproceedings{onose-etal-2019-sc,
title = "{SC}-{UPB} at the {V}ar{D}ial 2019 Evaluation Campaign: {M}oldavian vs. {R}omanian Cross-Dialect Topic Identification",
author = "Onose, Cristian and
Cercel, Dumitru-Clementin and
Trausan-Matu, Stefan",
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/W19-1418",
doi = "10.18653/v1/W19-1418",
pages = "172--177",
abstract = "This paper describes our models for the Moldavian vs. Romanian Cross-Topic Identification (MRC) evaluation campaign, part of the VarDial 2019 workshop. We focus on the three subtasks for MRC: binary classification between the Moldavian (MD) and the Romanian (RO) dialects and two cross-dialect multi-class classification between six news topics, MD to RO and RO to MD. We propose several deep learning models based on long short-term memory cells, Bidirectional Gated Recurrent Unit (BiGRU) and Hierarchical Attention Networks (HAN). We also employ three word embedding models to represent the text as a low dimensional vector. Our official submission includes two runs of the BiGRU and HAN models for each of the three subtasks. The best submitted model obtained the following macro-averaged F1 scores: 0.708 for subtask 1, 0.481 for subtask 2 and 0.480 for the last one. Due to a read error caused by the quoting behaviour over the test file, our final submissions contained a smaller number of items than expected. More than 50{\%} of the submission files were corrupted. Thus, we also present the results obtained with the corrected labels for which the HAN model achieves the following results: 0.930 for subtask 1, 0.590 for subtask 2 and 0.687 for the third one.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="onose-etal-2019-sc">
<titleInfo>
<title>SC-UPB at the VarDial 2019 Evaluation Campaign: Moldavian vs. Romanian Cross-Dialect Topic Identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cristian</namePart>
<namePart type="family">Onose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dumitru-Clementin</namePart>
<namePart type="family">Cercel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Trausan-Matu</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 our models for the Moldavian vs. Romanian Cross-Topic Identification (MRC) evaluation campaign, part of the VarDial 2019 workshop. We focus on the three subtasks for MRC: binary classification between the Moldavian (MD) and the Romanian (RO) dialects and two cross-dialect multi-class classification between six news topics, MD to RO and RO to MD. We propose several deep learning models based on long short-term memory cells, Bidirectional Gated Recurrent Unit (BiGRU) and Hierarchical Attention Networks (HAN). We also employ three word embedding models to represent the text as a low dimensional vector. Our official submission includes two runs of the BiGRU and HAN models for each of the three subtasks. The best submitted model obtained the following macro-averaged F1 scores: 0.708 for subtask 1, 0.481 for subtask 2 and 0.480 for the last one. Due to a read error caused by the quoting behaviour over the test file, our final submissions contained a smaller number of items than expected. More than 50% of the submission files were corrupted. Thus, we also present the results obtained with the corrected labels for which the HAN model achieves the following results: 0.930 for subtask 1, 0.590 for subtask 2 and 0.687 for the third one.</abstract>
<identifier type="citekey">onose-etal-2019-sc</identifier>
<identifier type="doi">10.18653/v1/W19-1418</identifier>
<location>
<url>https://aclanthology.org/W19-1418</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>172</start>
<end>177</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SC-UPB at the VarDial 2019 Evaluation Campaign: Moldavian vs. Romanian Cross-Dialect Topic Identification
%A Onose, Cristian
%A Cercel, Dumitru-Clementin
%A Trausan-Matu, Stefan
%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 onose-etal-2019-sc
%X This paper describes our models for the Moldavian vs. Romanian Cross-Topic Identification (MRC) evaluation campaign, part of the VarDial 2019 workshop. We focus on the three subtasks for MRC: binary classification between the Moldavian (MD) and the Romanian (RO) dialects and two cross-dialect multi-class classification between six news topics, MD to RO and RO to MD. We propose several deep learning models based on long short-term memory cells, Bidirectional Gated Recurrent Unit (BiGRU) and Hierarchical Attention Networks (HAN). We also employ three word embedding models to represent the text as a low dimensional vector. Our official submission includes two runs of the BiGRU and HAN models for each of the three subtasks. The best submitted model obtained the following macro-averaged F1 scores: 0.708 for subtask 1, 0.481 for subtask 2 and 0.480 for the last one. Due to a read error caused by the quoting behaviour over the test file, our final submissions contained a smaller number of items than expected. More than 50% of the submission files were corrupted. Thus, we also present the results obtained with the corrected labels for which the HAN model achieves the following results: 0.930 for subtask 1, 0.590 for subtask 2 and 0.687 for the third one.
%R 10.18653/v1/W19-1418
%U https://aclanthology.org/W19-1418
%U https://doi.org/10.18653/v1/W19-1418
%P 172-177
Markdown (Informal)
[SC-UPB at the VarDial 2019 Evaluation Campaign: Moldavian vs. Romanian Cross-Dialect Topic Identification](https://aclanthology.org/W19-1418) (Onose et al., VarDial 2019)
ACL