@inproceedings{butnaru-ionescu-2019-moroco,
title = "{MOROCO}: The {M}oldavian and {R}omanian Dialectal Corpus",
author = "Butnaru, Andrei and
Ionescu, Radu Tudor",
editor = "Korhonen, Anna and
Traum, David and
M{\`a}rquez, Llu{\'\i}s",
booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P19-1068",
doi = "10.18653/v1/P19-1068",
pages = "688--698",
abstract = "In this work, we introduce the MOldavian and ROmanian Dialectal COrpus (MOROCO), which is freely available for download at \url{https://github.com/butnaruandrei/MOROCO}. The corpus contains 33564 samples of text (with over 10 million tokens) collected from the news domain. The samples belong to one of the following six topics: culture, finance, politics, science, sports and tech. The data set is divided into 21719 samples for training, 5921 samples for validation and another 5924 samples for testing. For each sample, we provide corresponding dialectal and category labels. This allows us to perform empirical studies on several classification tasks such as (i) binary discrimination of Moldavian versus Romanian text samples, (ii) intra-dialect multi-class categorization by topic and (iii) cross-dialect multi-class categorization by topic. We perform experiments using a shallow approach based on string kernels, as well as a novel deep approach based on character-level convolutional neural networks containing Squeeze-and-Excitation blocks. We also present and analyze the most discriminative features of our best performing model, before and after named entity removal.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="butnaru-ionescu-2019-moroco">
<titleInfo>
<title>MOROCO: The Moldavian and Romanian Dialectal Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andrei</namePart>
<namePart type="family">Butnaru</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Radu</namePart>
<namePart type="given">Tudor</namePart>
<namePart type="family">Ionescu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Korhonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Traum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Màrquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this work, we introduce the MOldavian and ROmanian Dialectal COrpus (MOROCO), which is freely available for download at https://github.com/butnaruandrei/MOROCO. The corpus contains 33564 samples of text (with over 10 million tokens) collected from the news domain. The samples belong to one of the following six topics: culture, finance, politics, science, sports and tech. The data set is divided into 21719 samples for training, 5921 samples for validation and another 5924 samples for testing. For each sample, we provide corresponding dialectal and category labels. This allows us to perform empirical studies on several classification tasks such as (i) binary discrimination of Moldavian versus Romanian text samples, (ii) intra-dialect multi-class categorization by topic and (iii) cross-dialect multi-class categorization by topic. We perform experiments using a shallow approach based on string kernels, as well as a novel deep approach based on character-level convolutional neural networks containing Squeeze-and-Excitation blocks. We also present and analyze the most discriminative features of our best performing model, before and after named entity removal.</abstract>
<identifier type="citekey">butnaru-ionescu-2019-moroco</identifier>
<identifier type="doi">10.18653/v1/P19-1068</identifier>
<location>
<url>https://aclanthology.org/P19-1068</url>
</location>
<part>
<date>2019-07</date>
<extent unit="page">
<start>688</start>
<end>698</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MOROCO: The Moldavian and Romanian Dialectal Corpus
%A Butnaru, Andrei
%A Ionescu, Radu Tudor
%Y Korhonen, Anna
%Y Traum, David
%Y Màrquez, Lluís
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019
%8 July
%I Association for Computational Linguistics
%C Florence, Italy
%F butnaru-ionescu-2019-moroco
%X In this work, we introduce the MOldavian and ROmanian Dialectal COrpus (MOROCO), which is freely available for download at https://github.com/butnaruandrei/MOROCO. The corpus contains 33564 samples of text (with over 10 million tokens) collected from the news domain. The samples belong to one of the following six topics: culture, finance, politics, science, sports and tech. The data set is divided into 21719 samples for training, 5921 samples for validation and another 5924 samples for testing. For each sample, we provide corresponding dialectal and category labels. This allows us to perform empirical studies on several classification tasks such as (i) binary discrimination of Moldavian versus Romanian text samples, (ii) intra-dialect multi-class categorization by topic and (iii) cross-dialect multi-class categorization by topic. We perform experiments using a shallow approach based on string kernels, as well as a novel deep approach based on character-level convolutional neural networks containing Squeeze-and-Excitation blocks. We also present and analyze the most discriminative features of our best performing model, before and after named entity removal.
%R 10.18653/v1/P19-1068
%U https://aclanthology.org/P19-1068
%U https://doi.org/10.18653/v1/P19-1068
%P 688-698
Markdown (Informal)
[MOROCO: The Moldavian and Romanian Dialectal Corpus](https://aclanthology.org/P19-1068) (Butnaru & Ionescu, ACL 2019)
ACL
- Andrei Butnaru and Radu Tudor Ionescu. 2019. MOROCO: The Moldavian and Romanian Dialectal Corpus. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 688–698, Florence, Italy. Association for Computational Linguistics.