@inproceedings{tracey-strassel-2020-basic,
title = "Basic Language Resources for 31 Languages (Plus {E}nglish): The {LORELEI} Representative and Incident Language Packs",
author = "Tracey, Jennifer and
Strassel, Stephanie",
editor = "Beermann, Dorothee and
Besacier, Laurent and
Sakti, Sakriani and
Soria, Claudia",
booktitle = "Proceedings of the 1st Joint Workshop on Spoken Language Technologies for Under-resourced languages (SLTU) and Collaboration and Computing for Under-Resourced Languages (CCURL)",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources association",
url = "https://aclanthology.org/2020.sltu-1.39",
pages = "277--284",
abstract = "This paper documents and describes the thirty-one basic language resource packs created for the DARPA LORELEI program for use in development and testing of systems capable of providing language-independent situational awareness in emerging scenarios in a low resource language context. Twenty-four Representative Language Packs cover a broad range of language families and typologies, providing large volumes of monolingual and parallel text, smaller volumes of entity and semantic annotations, and a variety of grammatical resources and tools designed to support research into language universals and cross-language transfer. Seven Incident Language Packs provide test data to evaluate system capabilities on a previously unseen low resource language. We discuss the makeup of Representative and Incident Language Packs, the methods used to produce them, and the evolution of their design and implementation over the course of the multi-year LORELEI program. We conclude with a summary of the final language packs including their low-cost publication in the LDC catalog.",
language = "English",
ISBN = "979-10-95546-35-1",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tracey-strassel-2020-basic">
<titleInfo>
<title>Basic Language Resources for 31 Languages (Plus English): The LORELEI Representative and Incident Language Packs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jennifer</namePart>
<namePart type="family">Tracey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephanie</namePart>
<namePart type="family">Strassel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Joint Workshop on Spoken Language Technologies for Under-resourced languages (SLTU) and Collaboration and Computing for Under-Resourced Languages (CCURL)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dorothee</namePart>
<namePart type="family">Beermann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laurent</namePart>
<namePart type="family">Besacier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Soria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-35-1</identifier>
</relatedItem>
<abstract>This paper documents and describes the thirty-one basic language resource packs created for the DARPA LORELEI program for use in development and testing of systems capable of providing language-independent situational awareness in emerging scenarios in a low resource language context. Twenty-four Representative Language Packs cover a broad range of language families and typologies, providing large volumes of monolingual and parallel text, smaller volumes of entity and semantic annotations, and a variety of grammatical resources and tools designed to support research into language universals and cross-language transfer. Seven Incident Language Packs provide test data to evaluate system capabilities on a previously unseen low resource language. We discuss the makeup of Representative and Incident Language Packs, the methods used to produce them, and the evolution of their design and implementation over the course of the multi-year LORELEI program. We conclude with a summary of the final language packs including their low-cost publication in the LDC catalog.</abstract>
<identifier type="citekey">tracey-strassel-2020-basic</identifier>
<location>
<url>https://aclanthology.org/2020.sltu-1.39</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>277</start>
<end>284</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Basic Language Resources for 31 Languages (Plus English): The LORELEI Representative and Incident Language Packs
%A Tracey, Jennifer
%A Strassel, Stephanie
%Y Beermann, Dorothee
%Y Besacier, Laurent
%Y Sakti, Sakriani
%Y Soria, Claudia
%S Proceedings of the 1st Joint Workshop on Spoken Language Technologies for Under-resourced languages (SLTU) and Collaboration and Computing for Under-Resourced Languages (CCURL)
%D 2020
%8 May
%I European Language Resources association
%C Marseille, France
%@ 979-10-95546-35-1
%G English
%F tracey-strassel-2020-basic
%X This paper documents and describes the thirty-one basic language resource packs created for the DARPA LORELEI program for use in development and testing of systems capable of providing language-independent situational awareness in emerging scenarios in a low resource language context. Twenty-four Representative Language Packs cover a broad range of language families and typologies, providing large volumes of monolingual and parallel text, smaller volumes of entity and semantic annotations, and a variety of grammatical resources and tools designed to support research into language universals and cross-language transfer. Seven Incident Language Packs provide test data to evaluate system capabilities on a previously unseen low resource language. We discuss the makeup of Representative and Incident Language Packs, the methods used to produce them, and the evolution of their design and implementation over the course of the multi-year LORELEI program. We conclude with a summary of the final language packs including their low-cost publication in the LDC catalog.
%U https://aclanthology.org/2020.sltu-1.39
%P 277-284
Markdown (Informal)
[Basic Language Resources for 31 Languages (Plus English): The LORELEI Representative and Incident Language Packs](https://aclanthology.org/2020.sltu-1.39) (Tracey & Strassel, SLTU 2020)
ACL