@inproceedings{bogantes-etal-2016-towards,
title = "Towards Lexical Encoding of Multi-Word Expressions in {S}panish Dialects",
author = "Bogantes, Diana and
Rodr{\'\i}guez, Eric and
Arauco, Alejandro and
Rodr{\'\i}guez, Alejandro and
Savary, Agata",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1358",
pages = "2255--2261",
abstract = "This paper describes a pilot study in lexical encoding of multi-word expressions (MWEs) in 4 Latin American dialects of Spanish: Costa Rican, Colombian, Mexican and Peruvian. We describe the variability of MWE usage across dialects. We adapt an existing data model to a dialect-aware encoding, so as to represent dialect-related specificities, while avoiding redundancy of the data common for all dialects. A dozen of linguistic properties of MWEs can be expressed in this model, both on the level of a whole MWE and of its individual components. We describe the resulting lexical resource containing several dozens of MWEs in four dialects and we propose a method for constructing a web corpus as a support for crowdsourcing examples of MWE occurrences. The resource is available under an open license and paves the way towards a large-scale dialect-aware language resource construction, which should prove useful in both traditional and novel NLP applications.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bogantes-etal-2016-towards">
<titleInfo>
<title>Towards Lexical Encoding of Multi-Word Expressions in Spanish Dialects</title>
</titleInfo>
<name type="personal">
<namePart type="given">Diana</namePart>
<namePart type="family">Bogantes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Rodríguez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alejandro</namePart>
<namePart type="family">Arauco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alejandro</namePart>
<namePart type="family">Rodríguez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Agata</namePart>
<namePart type="family">Savary</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-may</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</title>
</titleInfo>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes a pilot study in lexical encoding of multi-word expressions (MWEs) in 4 Latin American dialects of Spanish: Costa Rican, Colombian, Mexican and Peruvian. We describe the variability of MWE usage across dialects. We adapt an existing data model to a dialect-aware encoding, so as to represent dialect-related specificities, while avoiding redundancy of the data common for all dialects. A dozen of linguistic properties of MWEs can be expressed in this model, both on the level of a whole MWE and of its individual components. We describe the resulting lexical resource containing several dozens of MWEs in four dialects and we propose a method for constructing a web corpus as a support for crowdsourcing examples of MWE occurrences. The resource is available under an open license and paves the way towards a large-scale dialect-aware language resource construction, which should prove useful in both traditional and novel NLP applications.</abstract>
<identifier type="citekey">bogantes-etal-2016-towards</identifier>
<location>
<url>https://aclanthology.org/L16-1358</url>
</location>
<part>
<date>2016-may</date>
<extent unit="page">
<start>2255</start>
<end>2261</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Lexical Encoding of Multi-Word Expressions in Spanish Dialects
%A Bogantes, Diana
%A Rodríguez, Eric
%A Arauco, Alejandro
%A Rodríguez, Alejandro
%A Savary, Agata
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 may
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F bogantes-etal-2016-towards
%X This paper describes a pilot study in lexical encoding of multi-word expressions (MWEs) in 4 Latin American dialects of Spanish: Costa Rican, Colombian, Mexican and Peruvian. We describe the variability of MWE usage across dialects. We adapt an existing data model to a dialect-aware encoding, so as to represent dialect-related specificities, while avoiding redundancy of the data common for all dialects. A dozen of linguistic properties of MWEs can be expressed in this model, both on the level of a whole MWE and of its individual components. We describe the resulting lexical resource containing several dozens of MWEs in four dialects and we propose a method for constructing a web corpus as a support for crowdsourcing examples of MWE occurrences. The resource is available under an open license and paves the way towards a large-scale dialect-aware language resource construction, which should prove useful in both traditional and novel NLP applications.
%U https://aclanthology.org/L16-1358
%P 2255-2261
Markdown (Informal)
[Towards Lexical Encoding of Multi-Word Expressions in Spanish Dialects](https://aclanthology.org/L16-1358) (Bogantes et al., LREC 2016)
ACL
- Diana Bogantes, Eric Rodríguez, Alejandro Arauco, Alejandro Rodríguez, and Agata Savary. 2016. Towards Lexical Encoding of Multi-Word Expressions in Spanish Dialects. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 2255–2261, Portorož, Slovenia. European Language Resources Association (ELRA).