@inproceedings{guenoune-etal-2020-dataset,
title = "A Dataset for Anaphora Analysis in {F}rench Emails",
author = "Guenoune, Hani and
Cousot, Kevin and
Lafourcade, Mathieu and
Mekaoui, Melissa and
Lopez, C{\'e}dric",
editor = "Ogrodniczuk, Maciej and
Ng, Vincent and
Grishina, Yulia and
Pradhan, Sameer",
booktitle = "Proceedings of the Third Workshop on Computational Models of Reference, Anaphora and Coreference",
month = dec,
year = "2020",
address = "Barcelona, Spain (online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.crac-1.17",
pages = "165--175",
abstract = "In 2019, about 293 billion emails were sent worldwide every day. They are a valuable source of information and knowledge for professionals. Since the 90{'}s, many studies have been done on emails and have highlighted the need for resources regarding numerous NLP tasks. Due to the lack of available resources for French, very few studies on emails have been conducted. Anaphora resolution in emails is an unexplored area, annotated resources are needed, at least to answer a first question: Does email communication have specifics that must be addressed to tackle the anaphora resolution task? In order to answer this question 1) we build a French emails corpus composed of 100 anonymized professional threads and make it available freely for scientific exploitation. 2) we provide annotations of anaphoric links in the email collection.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guenoune-etal-2020-dataset">
<titleInfo>
<title>A Dataset for Anaphora Analysis in French Emails</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hani</namePart>
<namePart type="family">Guenoune</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Cousot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mathieu</namePart>
<namePart type="family">Lafourcade</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Melissa</namePart>
<namePart type="family">Mekaoui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cédric</namePart>
<namePart type="family">Lopez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Computational Models of Reference, Anaphora and Coreference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maciej</namePart>
<namePart type="family">Ogrodniczuk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulia</namePart>
<namePart type="family">Grishina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sameer</namePart>
<namePart type="family">Pradhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In 2019, about 293 billion emails were sent worldwide every day. They are a valuable source of information and knowledge for professionals. Since the 90’s, many studies have been done on emails and have highlighted the need for resources regarding numerous NLP tasks. Due to the lack of available resources for French, very few studies on emails have been conducted. Anaphora resolution in emails is an unexplored area, annotated resources are needed, at least to answer a first question: Does email communication have specifics that must be addressed to tackle the anaphora resolution task? In order to answer this question 1) we build a French emails corpus composed of 100 anonymized professional threads and make it available freely for scientific exploitation. 2) we provide annotations of anaphoric links in the email collection.</abstract>
<identifier type="citekey">guenoune-etal-2020-dataset</identifier>
<location>
<url>https://aclanthology.org/2020.crac-1.17</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>165</start>
<end>175</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Dataset for Anaphora Analysis in French Emails
%A Guenoune, Hani
%A Cousot, Kevin
%A Lafourcade, Mathieu
%A Mekaoui, Melissa
%A Lopez, Cédric
%Y Ogrodniczuk, Maciej
%Y Ng, Vincent
%Y Grishina, Yulia
%Y Pradhan, Sameer
%S Proceedings of the Third Workshop on Computational Models of Reference, Anaphora and Coreference
%D 2020
%8 December
%I Association for Computational Linguistics
%C Barcelona, Spain (online)
%F guenoune-etal-2020-dataset
%X In 2019, about 293 billion emails were sent worldwide every day. They are a valuable source of information and knowledge for professionals. Since the 90’s, many studies have been done on emails and have highlighted the need for resources regarding numerous NLP tasks. Due to the lack of available resources for French, very few studies on emails have been conducted. Anaphora resolution in emails is an unexplored area, annotated resources are needed, at least to answer a first question: Does email communication have specifics that must be addressed to tackle the anaphora resolution task? In order to answer this question 1) we build a French emails corpus composed of 100 anonymized professional threads and make it available freely for scientific exploitation. 2) we provide annotations of anaphoric links in the email collection.
%U https://aclanthology.org/2020.crac-1.17
%P 165-175
Markdown (Informal)
[A Dataset for Anaphora Analysis in French Emails](https://aclanthology.org/2020.crac-1.17) (Guenoune et al., CRAC 2020)
ACL
- Hani Guenoune, Kevin Cousot, Mathieu Lafourcade, Melissa Mekaoui, and Cédric Lopez. 2020. A Dataset for Anaphora Analysis in French Emails. In Proceedings of the Third Workshop on Computational Models of Reference, Anaphora and Coreference, pages 165–175, Barcelona, Spain (online). Association for Computational Linguistics.