@inproceedings{strassel-tracey-2016-lorelei,
title = "{LORELEI} Language Packs: Data, Tools, and Resources for Technology Development in Low Resource Languages",
author = "Strassel, Stephanie and
Tracey, Jennifer",
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/L16-1521",
pages = "3273--3280",
abstract = "In this paper, we describe the textual linguistic resources in nearly 3 dozen languages being produced by Linguistic Data Consortium for DARPA{'}s LORELEI (Low Resource Languages for Emergent Incidents) Program. The goal of LORELEI is to improve the performance of human language technologies for low-resource languages and enable rapid re-training of such technologies for new languages, with a focus on the use case of deployment of resources in sudden emergencies such as natural disasters. Representative languages have been selected to provide broad typological coverage for training, and surprise incident languages for testing will be selected over the course of the program. Our approach treats the full set of language packs as a coherent whole, maintaining LORELEI-wide specifications, tagsets, and guidelines, while allowing for adaptation to the specific needs created by each language. Each representative language corpus, therefore, both stands on its own as a resource for the specific language and forms part of a large multilingual resource for broader cross-language technology development.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="strassel-tracey-2016-lorelei">
<titleInfo>
<title>LORELEI Language Packs: Data, Tools, and Resources for Technology Development in Low Resource Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stephanie</namePart>
<namePart type="family">Strassel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jennifer</namePart>
<namePart type="family">Tracey</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>In this paper, we describe the textual linguistic resources in nearly 3 dozen languages being produced by Linguistic Data Consortium for DARPA’s LORELEI (Low Resource Languages for Emergent Incidents) Program. The goal of LORELEI is to improve the performance of human language technologies for low-resource languages and enable rapid re-training of such technologies for new languages, with a focus on the use case of deployment of resources in sudden emergencies such as natural disasters. Representative languages have been selected to provide broad typological coverage for training, and surprise incident languages for testing will be selected over the course of the program. Our approach treats the full set of language packs as a coherent whole, maintaining LORELEI-wide specifications, tagsets, and guidelines, while allowing for adaptation to the specific needs created by each language. Each representative language corpus, therefore, both stands on its own as a resource for the specific language and forms part of a large multilingual resource for broader cross-language technology development.</abstract>
<identifier type="citekey">strassel-tracey-2016-lorelei</identifier>
<location>
<url>https://aclanthology.org/L16-1521</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>3273</start>
<end>3280</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LORELEI Language Packs: Data, Tools, and Resources for Technology Development in Low Resource Languages
%A Strassel, Stephanie
%A Tracey, Jennifer
%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 strassel-tracey-2016-lorelei
%X In this paper, we describe the textual linguistic resources in nearly 3 dozen languages being produced by Linguistic Data Consortium for DARPA’s LORELEI (Low Resource Languages for Emergent Incidents) Program. The goal of LORELEI is to improve the performance of human language technologies for low-resource languages and enable rapid re-training of such technologies for new languages, with a focus on the use case of deployment of resources in sudden emergencies such as natural disasters. Representative languages have been selected to provide broad typological coverage for training, and surprise incident languages for testing will be selected over the course of the program. Our approach treats the full set of language packs as a coherent whole, maintaining LORELEI-wide specifications, tagsets, and guidelines, while allowing for adaptation to the specific needs created by each language. Each representative language corpus, therefore, both stands on its own as a resource for the specific language and forms part of a large multilingual resource for broader cross-language technology development.
%U https://aclanthology.org/L16-1521
%P 3273-3280
Markdown (Informal)
[LORELEI Language Packs: Data, Tools, and Resources for Technology Development in Low Resource Languages](https://aclanthology.org/L16-1521) (Strassel & Tracey, LREC 2016)
ACL