@inproceedings{ortmann-dipper-2020-automatic,
title = "Automatic Orality Identification in Historical Texts",
author = "Ortmann, Katrin and
Dipper, Stefanie",
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
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.162/",
pages = "1293--1302",
language = "eng",
ISBN = "979-10-95546-34-4",
abstract = "Independently of the medial representation (written/spoken), language can exhibit characteristics of conceptual orality or literacy, which mainly manifest themselves on the lexical or syntactic level. In this paper we aim at automatically identifying conceptually-oral historical texts, with the ultimate goal of gaining knowledge about spoken data of historical time stages. We apply a set of general linguistic features that have been proven to be effective for the classification of modern language data to historical German texts from various registers. Many of the features turn out to be equally useful in determining the conceptuality of historical data as they are for modern data, especially the frequency of different types of pronouns and the ratio of verbs to nouns. Other features like sentence length, particles or interjections point to peculiarities of the historical data and reveal problems with the adoption of a feature set that was developed on modern language data."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ortmann-dipper-2020-automatic">
<titleInfo>
<title>Automatic Orality Identification in Historical Texts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Katrin</namePart>
<namePart type="family">Ortmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefanie</namePart>
<namePart type="family">Dipper</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth 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">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</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Independently of the medial representation (written/spoken), language can exhibit characteristics of conceptual orality or literacy, which mainly manifest themselves on the lexical or syntactic level. In this paper we aim at automatically identifying conceptually-oral historical texts, with the ultimate goal of gaining knowledge about spoken data of historical time stages. We apply a set of general linguistic features that have been proven to be effective for the classification of modern language data to historical German texts from various registers. Many of the features turn out to be equally useful in determining the conceptuality of historical data as they are for modern data, especially the frequency of different types of pronouns and the ratio of verbs to nouns. Other features like sentence length, particles or interjections point to peculiarities of the historical data and reveal problems with the adoption of a feature set that was developed on modern language data.</abstract>
<identifier type="citekey">ortmann-dipper-2020-automatic</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.162/</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>1293</start>
<end>1302</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Orality Identification in Historical Texts
%A Ortmann, Katrin
%A Dipper, Stefanie
%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 Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G eng
%F ortmann-dipper-2020-automatic
%X Independently of the medial representation (written/spoken), language can exhibit characteristics of conceptual orality or literacy, which mainly manifest themselves on the lexical or syntactic level. In this paper we aim at automatically identifying conceptually-oral historical texts, with the ultimate goal of gaining knowledge about spoken data of historical time stages. We apply a set of general linguistic features that have been proven to be effective for the classification of modern language data to historical German texts from various registers. Many of the features turn out to be equally useful in determining the conceptuality of historical data as they are for modern data, especially the frequency of different types of pronouns and the ratio of verbs to nouns. Other features like sentence length, particles or interjections point to peculiarities of the historical data and reveal problems with the adoption of a feature set that was developed on modern language data.
%U https://aclanthology.org/2020.lrec-1.162/
%P 1293-1302
Markdown (Informal)
[Automatic Orality Identification in Historical Texts](https://aclanthology.org/2020.lrec-1.162/) (Ortmann & Dipper, LREC 2020)
ACL