@inproceedings{sylak-glassman-etal-2016-remote,
title = "Remote Elicitation of Inflectional Paradigms to Seed Morphological Analysis in Low-Resource Languages",
author = "Sylak-Glassman, John and
Kirov, Christo and
Yarowsky, David",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
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/L16-1497",
pages = "3116--3120",
abstract = "Structured, complete inflectional paradigm data exists for very few of the world{'}s languages, but is crucial to training morphological analysis tools. We present methods inspired by linguistic fieldwork for gathering inflectional paradigm data in a machine-readable, interoperable format from remotely-located speakers of any language. Informants are tasked with completing language-specific paradigm elicitation templates. Templates are constructed by linguists using grammatical reference materials to ensure completeness. Each cell in a template is associated with contextual prompts designed to help informants with varying levels of linguistic expertise (from professional translators to untrained native speakers) provide the desired inflected form. To facilitate downstream use in interoperable NLP/HLT applications, each cell is also associated with a language-independent machine-readable set of morphological tags from the UniMorph Schema. This data is useful for seeding morphological analysis and generation software, particularly when the data is representative of the range of surface morphological variation in the language. At present, we have obtained 792 lemmas and 25,056 inflected forms from 15 languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sylak-glassman-etal-2016-remote">
<titleInfo>
<title>Remote Elicitation of Inflectional Paradigms to Seed Morphological Analysis in Low-Resource Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Sylak-Glassman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christo</namePart>
<namePart type="family">Kirov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Yarowsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</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>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helene</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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>Structured, complete inflectional paradigm data exists for very few of the world’s languages, but is crucial to training morphological analysis tools. We present methods inspired by linguistic fieldwork for gathering inflectional paradigm data in a machine-readable, interoperable format from remotely-located speakers of any language. Informants are tasked with completing language-specific paradigm elicitation templates. Templates are constructed by linguists using grammatical reference materials to ensure completeness. Each cell in a template is associated with contextual prompts designed to help informants with varying levels of linguistic expertise (from professional translators to untrained native speakers) provide the desired inflected form. To facilitate downstream use in interoperable NLP/HLT applications, each cell is also associated with a language-independent machine-readable set of morphological tags from the UniMorph Schema. This data is useful for seeding morphological analysis and generation software, particularly when the data is representative of the range of surface morphological variation in the language. At present, we have obtained 792 lemmas and 25,056 inflected forms from 15 languages.</abstract>
<identifier type="citekey">sylak-glassman-etal-2016-remote</identifier>
<location>
<url>https://aclanthology.org/L16-1497</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>3116</start>
<end>3120</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Remote Elicitation of Inflectional Paradigms to Seed Morphological Analysis in Low-Resource Languages
%A Sylak-Glassman, John
%A Kirov, Christo
%A Yarowsky, David
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%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 sylak-glassman-etal-2016-remote
%X Structured, complete inflectional paradigm data exists for very few of the world’s languages, but is crucial to training morphological analysis tools. We present methods inspired by linguistic fieldwork for gathering inflectional paradigm data in a machine-readable, interoperable format from remotely-located speakers of any language. Informants are tasked with completing language-specific paradigm elicitation templates. Templates are constructed by linguists using grammatical reference materials to ensure completeness. Each cell in a template is associated with contextual prompts designed to help informants with varying levels of linguistic expertise (from professional translators to untrained native speakers) provide the desired inflected form. To facilitate downstream use in interoperable NLP/HLT applications, each cell is also associated with a language-independent machine-readable set of morphological tags from the UniMorph Schema. This data is useful for seeding morphological analysis and generation software, particularly when the data is representative of the range of surface morphological variation in the language. At present, we have obtained 792 lemmas and 25,056 inflected forms from 15 languages.
%U https://aclanthology.org/L16-1497
%P 3116-3120
Markdown (Informal)
[Remote Elicitation of Inflectional Paradigms to Seed Morphological Analysis in Low-Resource Languages](https://aclanthology.org/L16-1497) (Sylak-Glassman et al., LREC 2016)
ACL