@inproceedings{macken-etal-2012-keystrokes,
title = "From keystrokes to annotated process data: Enriching the output of Inputlog with linguistic information",
author = {Macken, Lieve and
Hoste, Veronique and
Leijten, Mari{\"e}lle and
Van Waes, Luuk},
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/161_Paper.pdf",
pages = "2224--2229",
abstract = "Keystroke logging tools are a valuable aid to monitor written language production. These tools record all keystrokes, including backspaces and deletions together with timing information. In this paper we report on an extension to the keystroke logging program Inputlog in which we aggregate the logged process data from the keystroke (character) level to the word level. The logged process data are further enriched with different kinds of linguistic information: part-of-speech tags, lemmata, chunk boundaries, syllable boundaries and word frequency. A dedicated parser has been developed that distils from the logged process data word-level revisions, deleted fragments and final product data. The linguistically-annotated output will facilitate the linguistic analysis of the logged data and will provide a valuable basis for more linguistically-oriented writing process research. The set-up of the extension to Inputlog is largely language-independent. As proof-of-concept, the extension has been developed for English and Dutch. Inputlog is freely available for research purposes.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="macken-etal-2012-keystrokes">
<titleInfo>
<title>From keystrokes to annotated process data: Enriching the output of Inputlog with linguistic information</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lieve</namePart>
<namePart type="family">Macken</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mariëlle</namePart>
<namePart type="family">Leijten</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luuk</namePart>
<namePart type="family">Van Waes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Keystroke logging tools are a valuable aid to monitor written language production. These tools record all keystrokes, including backspaces and deletions together with timing information. In this paper we report on an extension to the keystroke logging program Inputlog in which we aggregate the logged process data from the keystroke (character) level to the word level. The logged process data are further enriched with different kinds of linguistic information: part-of-speech tags, lemmata, chunk boundaries, syllable boundaries and word frequency. A dedicated parser has been developed that distils from the logged process data word-level revisions, deleted fragments and final product data. The linguistically-annotated output will facilitate the linguistic analysis of the logged data and will provide a valuable basis for more linguistically-oriented writing process research. The set-up of the extension to Inputlog is largely language-independent. As proof-of-concept, the extension has been developed for English and Dutch. Inputlog is freely available for research purposes.</abstract>
<identifier type="citekey">macken-etal-2012-keystrokes</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/161_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>2224</start>
<end>2229</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From keystrokes to annotated process data: Enriching the output of Inputlog with linguistic information
%A Macken, Lieve
%A Hoste, Veronique
%A Leijten, Mariëlle
%A Van Waes, Luuk
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F macken-etal-2012-keystrokes
%X Keystroke logging tools are a valuable aid to monitor written language production. These tools record all keystrokes, including backspaces and deletions together with timing information. In this paper we report on an extension to the keystroke logging program Inputlog in which we aggregate the logged process data from the keystroke (character) level to the word level. The logged process data are further enriched with different kinds of linguistic information: part-of-speech tags, lemmata, chunk boundaries, syllable boundaries and word frequency. A dedicated parser has been developed that distils from the logged process data word-level revisions, deleted fragments and final product data. The linguistically-annotated output will facilitate the linguistic analysis of the logged data and will provide a valuable basis for more linguistically-oriented writing process research. The set-up of the extension to Inputlog is largely language-independent. As proof-of-concept, the extension has been developed for English and Dutch. Inputlog is freely available for research purposes.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/161_Paper.pdf
%P 2224-2229
Markdown (Informal)
[From keystrokes to annotated process data: Enriching the output of Inputlog with linguistic information](http://www.lrec-conf.org/proceedings/lrec2012/pdf/161_Paper.pdf) (Macken et al., LREC 2012)
ACL