@inproceedings{miletic-etal-2022-pro,
title = "Pro-{TEXT}: an Annotated Corpus of Keystroke Logs",
author = "Miletic, Aleksandra and
Benzitoun, Christophe and
Cislaru, Georgeta and
Herrera-Yanez, Santiago",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.184/",
pages = "1732--1739",
abstract = "Pro-TEXT is a corpus of keystroke logs written in French. Keystroke logs are recordings of the writing process executed through a keyboard, which keep track of all actions taken by the writer (character additions, deletions, substitutions). As such, the Pro-TEXT corpus offers new insights into text genesis and underlying cognitive processes from the production perspective. A subset of the corpus is linguistically annotated with parts of speech, lemmas and syntactic dependencies, making it suitable for the study of interactions between linguistic and behavioural aspects of the writing process. The full corpus contains 202K tokens, while the annotated portion is currently 30K tokens large. The annotated content is progressively being made available in a database-like CSV format and in CoNLL format, and the work on an HTML-based visualisation tool is currently under way. To the best of our knowledge, Pro-TEXT is the first corpus of its kind in French."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="miletic-etal-2022-pro">
<titleInfo>
<title>Pro-TEXT: an Annotated Corpus of Keystroke Logs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aleksandra</namePart>
<namePart type="family">Miletic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christophe</namePart>
<namePart type="family">Benzitoun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georgeta</namePart>
<namePart type="family">Cislaru</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Santiago</namePart>
<namePart type="family">Herrera-Yanez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</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">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</namePart>
<namePart type="family">Mazo</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</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Pro-TEXT is a corpus of keystroke logs written in French. Keystroke logs are recordings of the writing process executed through a keyboard, which keep track of all actions taken by the writer (character additions, deletions, substitutions). As such, the Pro-TEXT corpus offers new insights into text genesis and underlying cognitive processes from the production perspective. A subset of the corpus is linguistically annotated with parts of speech, lemmas and syntactic dependencies, making it suitable for the study of interactions between linguistic and behavioural aspects of the writing process. The full corpus contains 202K tokens, while the annotated portion is currently 30K tokens large. The annotated content is progressively being made available in a database-like CSV format and in CoNLL format, and the work on an HTML-based visualisation tool is currently under way. To the best of our knowledge, Pro-TEXT is the first corpus of its kind in French.</abstract>
<identifier type="citekey">miletic-etal-2022-pro</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.184/</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>1732</start>
<end>1739</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Pro-TEXT: an Annotated Corpus of Keystroke Logs
%A Miletic, Aleksandra
%A Benzitoun, Christophe
%A Cislaru, Georgeta
%A Herrera-Yanez, Santiago
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F miletic-etal-2022-pro
%X Pro-TEXT is a corpus of keystroke logs written in French. Keystroke logs are recordings of the writing process executed through a keyboard, which keep track of all actions taken by the writer (character additions, deletions, substitutions). As such, the Pro-TEXT corpus offers new insights into text genesis and underlying cognitive processes from the production perspective. A subset of the corpus is linguistically annotated with parts of speech, lemmas and syntactic dependencies, making it suitable for the study of interactions between linguistic and behavioural aspects of the writing process. The full corpus contains 202K tokens, while the annotated portion is currently 30K tokens large. The annotated content is progressively being made available in a database-like CSV format and in CoNLL format, and the work on an HTML-based visualisation tool is currently under way. To the best of our knowledge, Pro-TEXT is the first corpus of its kind in French.
%U https://aclanthology.org/2022.lrec-1.184/
%P 1732-1739
Markdown (Informal)
[Pro-TEXT: an Annotated Corpus of Keystroke Logs](https://aclanthology.org/2022.lrec-1.184/) (Miletic et al., LREC 2022)
ACL
- Aleksandra Miletic, Christophe Benzitoun, Georgeta Cislaru, and Santiago Herrera-Yanez. 2022. Pro-TEXT: an Annotated Corpus of Keystroke Logs. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 1732–1739, Marseille, France. European Language Resources Association.