@inproceedings{song-etal-2014-collecting,
title = "Collecting Natural {SMS} and Chat Conversations in Multiple Languages: The {BOLT} Phase 2 Corpus",
author = "Song, Zhiyi and
Strassel, Stephanie and
Lee, Haejoong and
Walker, Kevin and
Wright, Jonathan and
Garland, Jennifer and
Fore, Dana and
Gainor, Brian and
Cabe, Preston and
Thomas, Thomas and
Callahan, Brendan and
Sawyer, Ann",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L14-1071/",
pages = "1699--1704",
abstract = "The DARPA BOLT Program develops systems capable of allowing English speakers to retrieve and understand information from informal foreign language genres. Phase 2 of the program required large volumes of naturally occurring informal text (SMS) and chat messages from individual users in multiple languages to support evaluation of machine translation systems. We describe the design and implementation of a robust collection system capable of capturing both live and archived SMS and chat conversations from willing participants. We also discuss the challenges recruitment at a time when potential participants have acute and growing concerns about their personal privacy in the realm of digital communication, and we outline the techniques adopted to confront those challenges. Finally, we review the properties of the resulting BOLT Phase 2 Corpus, which comprises over 6.5 million words of naturally-occurring chat and SMS in English, Chinese and Egyptian Arabic."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="song-etal-2014-collecting">
<titleInfo>
<title>Collecting Natural SMS and Chat Conversations in Multiple Languages: The BOLT Phase 2 Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhiyi</namePart>
<namePart type="family">Song</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>
<name type="personal">
<namePart type="given">Haejoong</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Walker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Wright</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jennifer</namePart>
<namePart type="family">Garland</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dana</namePart>
<namePart type="family">Fore</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brian</namePart>
<namePart type="family">Gainor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preston</namePart>
<namePart type="family">Cabe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Thomas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brendan</namePart>
<namePart type="family">Callahan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ann</namePart>
<namePart type="family">Sawyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Hrafn</namePart>
<namePart type="family">Loftsson</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">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">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The DARPA BOLT Program develops systems capable of allowing English speakers to retrieve and understand information from informal foreign language genres. Phase 2 of the program required large volumes of naturally occurring informal text (SMS) and chat messages from individual users in multiple languages to support evaluation of machine translation systems. We describe the design and implementation of a robust collection system capable of capturing both live and archived SMS and chat conversations from willing participants. We also discuss the challenges recruitment at a time when potential participants have acute and growing concerns about their personal privacy in the realm of digital communication, and we outline the techniques adopted to confront those challenges. Finally, we review the properties of the resulting BOLT Phase 2 Corpus, which comprises over 6.5 million words of naturally-occurring chat and SMS in English, Chinese and Egyptian Arabic.</abstract>
<identifier type="citekey">song-etal-2014-collecting</identifier>
<location>
<url>https://aclanthology.org/L14-1071/</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>1699</start>
<end>1704</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Collecting Natural SMS and Chat Conversations in Multiple Languages: The BOLT Phase 2 Corpus
%A Song, Zhiyi
%A Strassel, Stephanie
%A Lee, Haejoong
%A Walker, Kevin
%A Wright, Jonathan
%A Garland, Jennifer
%A Fore, Dana
%A Gainor, Brian
%A Cabe, Preston
%A Thomas, Thomas
%A Callahan, Brendan
%A Sawyer, Ann
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F song-etal-2014-collecting
%X The DARPA BOLT Program develops systems capable of allowing English speakers to retrieve and understand information from informal foreign language genres. Phase 2 of the program required large volumes of naturally occurring informal text (SMS) and chat messages from individual users in multiple languages to support evaluation of machine translation systems. We describe the design and implementation of a robust collection system capable of capturing both live and archived SMS and chat conversations from willing participants. We also discuss the challenges recruitment at a time when potential participants have acute and growing concerns about their personal privacy in the realm of digital communication, and we outline the techniques adopted to confront those challenges. Finally, we review the properties of the resulting BOLT Phase 2 Corpus, which comprises over 6.5 million words of naturally-occurring chat and SMS in English, Chinese and Egyptian Arabic.
%U https://aclanthology.org/L14-1071/
%P 1699-1704
Markdown (Informal)
[Collecting Natural SMS and Chat Conversations in Multiple Languages: The BOLT Phase 2 Corpus](https://aclanthology.org/L14-1071/) (Song et al., LREC 2014)
ACL
- Zhiyi Song, Stephanie Strassel, Haejoong Lee, Kevin Walker, Jonathan Wright, Jennifer Garland, Dana Fore, Brian Gainor, Preston Cabe, Thomas Thomas, Brendan Callahan, and Ann Sawyer. 2014. Collecting Natural SMS and Chat Conversations in Multiple Languages: The BOLT Phase 2 Corpus. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 1699–1704, Reykjavik, Iceland. European Language Resources Association (ELRA).