@inproceedings{montano-etal-2019-parallel,
title = "A Parallel Corpus {M}ixtec-{S}panish",
author = "Monta{\~n}o, Cynthia and
Sierra Mart{\'\i}nez, Gerardo and
Bel-Enguix, Gemma and
Gomez, Helena",
editor = "Axelrod, Amittai and
Yang, Diyi and
Cunha, Rossana and
Shaikh, Samira and
Waseem, Zeerak",
booktitle = "Proceedings of the 2019 Workshop on Widening NLP",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-3650",
pages = "157--159",
abstract = "This work is about the compilation process of parallel documents Spanish-Mixtec. There are not many Spanish-Mixec parallel texts and most of the sources are non-digital books. Due to this, we need to face the errors when digitizing the sources and difficulties in sentence alignment, as well as the fact that does not exist a standard orthography. Our parallel corpus consists of sixty texts coming from books and digital repositories. These documents belong to different domains: history, traditional stories, didactic material, recipes, ethnographical descriptions of each town and instruction manuals for disease prevention. We have classified this material in five major categories: didactic (6 texts), educative (6 texts), interpretative (7 texts), narrative (39 texts), and poetic (2 texts). The final total of tokens is 49,814 Spanish words and 47,774 Mixtec words. The texts belong to the states of Oaxaca (48 texts), Guerrero (9 texts) and Puebla (3 texts). According to this data, we see that the corpus is unbalanced in what refers to the representation of the different territories. While 55{\%} of speakers are in Oaxaca, 80{\%} of texts come from this region. Guerrero has the 30{\%} of speakers and the 15{\%} of texts and Puebla, with the 15{\%} of the speakers has a representation of the 5{\%} in the corpus.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="montano-etal-2019-parallel">
<titleInfo>
<title>A Parallel Corpus Mixtec-Spanish</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cynthia</namePart>
<namePart type="family">Montaño</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gerardo</namePart>
<namePart type="family">Sierra Martínez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gemma</namePart>
<namePart type="family">Bel-Enguix</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Workshop on Widening NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amittai</namePart>
<namePart type="family">Axelrod</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diyi</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rossana</namePart>
<namePart type="family">Cunha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samira</namePart>
<namePart type="family">Shaikh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zeerak</namePart>
<namePart type="family">Waseem</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>This work is about the compilation process of parallel documents Spanish-Mixtec. There are not many Spanish-Mixec parallel texts and most of the sources are non-digital books. Due to this, we need to face the errors when digitizing the sources and difficulties in sentence alignment, as well as the fact that does not exist a standard orthography. Our parallel corpus consists of sixty texts coming from books and digital repositories. These documents belong to different domains: history, traditional stories, didactic material, recipes, ethnographical descriptions of each town and instruction manuals for disease prevention. We have classified this material in five major categories: didactic (6 texts), educative (6 texts), interpretative (7 texts), narrative (39 texts), and poetic (2 texts). The final total of tokens is 49,814 Spanish words and 47,774 Mixtec words. The texts belong to the states of Oaxaca (48 texts), Guerrero (9 texts) and Puebla (3 texts). According to this data, we see that the corpus is unbalanced in what refers to the representation of the different territories. While 55% of speakers are in Oaxaca, 80% of texts come from this region. Guerrero has the 30% of speakers and the 15% of texts and Puebla, with the 15% of the speakers has a representation of the 5% in the corpus.</abstract>
<identifier type="citekey">montano-etal-2019-parallel</identifier>
<location>
<url>https://aclanthology.org/W19-3650</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>157</start>
<end>159</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Parallel Corpus Mixtec-Spanish
%A Montaño, Cynthia
%A Sierra Martínez, Gerardo
%A Bel-Enguix, Gemma
%A Gomez, Helena
%Y Axelrod, Amittai
%Y Yang, Diyi
%Y Cunha, Rossana
%Y Shaikh, Samira
%Y Waseem, Zeerak
%S Proceedings of the 2019 Workshop on Widening NLP
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence, Italy
%F montano-etal-2019-parallel
%X This work is about the compilation process of parallel documents Spanish-Mixtec. There are not many Spanish-Mixec parallel texts and most of the sources are non-digital books. Due to this, we need to face the errors when digitizing the sources and difficulties in sentence alignment, as well as the fact that does not exist a standard orthography. Our parallel corpus consists of sixty texts coming from books and digital repositories. These documents belong to different domains: history, traditional stories, didactic material, recipes, ethnographical descriptions of each town and instruction manuals for disease prevention. We have classified this material in five major categories: didactic (6 texts), educative (6 texts), interpretative (7 texts), narrative (39 texts), and poetic (2 texts). The final total of tokens is 49,814 Spanish words and 47,774 Mixtec words. The texts belong to the states of Oaxaca (48 texts), Guerrero (9 texts) and Puebla (3 texts). According to this data, we see that the corpus is unbalanced in what refers to the representation of the different territories. While 55% of speakers are in Oaxaca, 80% of texts come from this region. Guerrero has the 30% of speakers and the 15% of texts and Puebla, with the 15% of the speakers has a representation of the 5% in the corpus.
%U https://aclanthology.org/W19-3650
%P 157-159
Markdown (Informal)
[A Parallel Corpus Mixtec-Spanish](https://aclanthology.org/W19-3650) (Montaño et al., WiNLP 2019)
ACL
- Cynthia Montaño, Gerardo Sierra Martínez, Gemma Bel-Enguix, and Helena Gomez. 2019. A Parallel Corpus Mixtec-Spanish. In Proceedings of the 2019 Workshop on Widening NLP, pages 157–159, Florence, Italy. Association for Computational Linguistics.