@inproceedings{hernandez-etal-2016-ubuntu,
title = "{U}buntu-fr: A Large and Open Corpus for Multi-modal Analysis of Online Written Conversations",
author = "Hernandez, Nicolas and
Salim, Soufian and
Clouet, Elizaveta Loginova",
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/L16-1280",
pages = "1777--1783",
abstract = "We present a large, free, French corpus of online written conversations extracted from the Ubuntu platform{'}s forums, mailing lists and IRC channels. The corpus is meant to support multi-modality and diachronic studies of online written conversations. We choose to build the corpus around a robust metadata model based upon strong principles, such as the {``}stand off{''} annotation principle. We detail the model, we explain how the data was collected and processed - in terms of meta-data, text and conversation - and we detail the corpus{'}contents through a series of meaningful statistics. A portion of the corpus - about 4,700 sentences from emails, forum posts and chat messages sent in November 2014 - is annotated in terms of dialogue acts and sentiment. We discuss how we adapted our dialogue act taxonomy from the DIT++ annotation scheme and how the data was annotated, before presenting our results as well as a brief qualitative analysis of the annotated data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hernandez-etal-2016-ubuntu">
<titleInfo>
<title>Ubuntu-fr: A Large and Open Corpus for Multi-modal Analysis of Online Written Conversations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicolas</namePart>
<namePart type="family">Hernandez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soufian</namePart>
<namePart type="family">Salim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elizaveta</namePart>
<namePart type="given">Loginova</namePart>
<namePart type="family">Clouet</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>We present a large, free, French corpus of online written conversations extracted from the Ubuntu platform’s forums, mailing lists and IRC channels. The corpus is meant to support multi-modality and diachronic studies of online written conversations. We choose to build the corpus around a robust metadata model based upon strong principles, such as the “stand off” annotation principle. We detail the model, we explain how the data was collected and processed - in terms of meta-data, text and conversation - and we detail the corpus’contents through a series of meaningful statistics. A portion of the corpus - about 4,700 sentences from emails, forum posts and chat messages sent in November 2014 - is annotated in terms of dialogue acts and sentiment. We discuss how we adapted our dialogue act taxonomy from the DIT++ annotation scheme and how the data was annotated, before presenting our results as well as a brief qualitative analysis of the annotated data.</abstract>
<identifier type="citekey">hernandez-etal-2016-ubuntu</identifier>
<location>
<url>https://aclanthology.org/L16-1280</url>
</location>
<part>
<date>2016-may</date>
<extent unit="page">
<start>1777</start>
<end>1783</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Ubuntu-fr: A Large and Open Corpus for Multi-modal Analysis of Online Written Conversations
%A Hernandez, Nicolas
%A Salim, Soufian
%A Clouet, Elizaveta Loginova
%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 hernandez-etal-2016-ubuntu
%X We present a large, free, French corpus of online written conversations extracted from the Ubuntu platform’s forums, mailing lists and IRC channels. The corpus is meant to support multi-modality and diachronic studies of online written conversations. We choose to build the corpus around a robust metadata model based upon strong principles, such as the “stand off” annotation principle. We detail the model, we explain how the data was collected and processed - in terms of meta-data, text and conversation - and we detail the corpus’contents through a series of meaningful statistics. A portion of the corpus - about 4,700 sentences from emails, forum posts and chat messages sent in November 2014 - is annotated in terms of dialogue acts and sentiment. We discuss how we adapted our dialogue act taxonomy from the DIT++ annotation scheme and how the data was annotated, before presenting our results as well as a brief qualitative analysis of the annotated data.
%U https://aclanthology.org/L16-1280
%P 1777-1783
Markdown (Informal)
[Ubuntu-fr: A Large and Open Corpus for Multi-modal Analysis of Online Written Conversations](https://aclanthology.org/L16-1280) (Hernandez et al., LREC 2016)
ACL