@inproceedings{kermes-etal-2016-royal,
title = "The Royal Society Corpus: From Uncharted Data to Corpus",
author = {Kermes, Hannah and
Degaetano-Ortlieb, Stefania and
Khamis, Ashraf and
Knappen, J{\"o}rg and
Teich, Elke},
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
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/L16-1305",
pages = "1928--1931",
abstract = "We present the Royal Society Corpus (RSC) built from the Philosophical Transactions and Proceedings of the Royal Society of London. At present, the corpus contains articles from the first two centuries of the journal (1665―1869) and amounts to around 35 million tokens. The motivation for building the RSC is to investigate the diachronic linguistic development of scientific English. Specifically, we assume that due to specialization, linguistic encodings become more compact over time (Halliday, 1988; Halliday and Martin, 1993), thus creating a specific discourse type characterized by high information density that is functional for expert communication. When building corpora from uncharted material, typically not all relevant meta-data (e.g. author, time, genre) or linguistic data (e.g. sentence/word boundaries, words, parts of speech) is readily available. We present an approach to obtain good quality meta-data and base text data adopting the concept of Agile Software Development.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kermes-etal-2016-royal">
<titleInfo>
<title>The Royal Society Corpus: From Uncharted Data to Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hannah</namePart>
<namePart type="family">Kermes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefania</namePart>
<namePart type="family">Degaetano-Ortlieb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashraf</namePart>
<namePart type="family">Khamis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jörg</namePart>
<namePart type="family">Knappen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elke</namePart>
<namePart type="family">Teich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</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>
<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">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</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">Helene</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 (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present the Royal Society Corpus (RSC) built from the Philosophical Transactions and Proceedings of the Royal Society of London. At present, the corpus contains articles from the first two centuries of the journal (1665―1869) and amounts to around 35 million tokens. The motivation for building the RSC is to investigate the diachronic linguistic development of scientific English. Specifically, we assume that due to specialization, linguistic encodings become more compact over time (Halliday, 1988; Halliday and Martin, 1993), thus creating a specific discourse type characterized by high information density that is functional for expert communication. When building corpora from uncharted material, typically not all relevant meta-data (e.g. author, time, genre) or linguistic data (e.g. sentence/word boundaries, words, parts of speech) is readily available. We present an approach to obtain good quality meta-data and base text data adopting the concept of Agile Software Development.</abstract>
<identifier type="citekey">kermes-etal-2016-royal</identifier>
<location>
<url>https://aclanthology.org/L16-1305</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>1928</start>
<end>1931</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Royal Society Corpus: From Uncharted Data to Corpus
%A Kermes, Hannah
%A Degaetano-Ortlieb, Stefania
%A Khamis, Ashraf
%A Knappen, Jörg
%A Teich, Elke
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%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 kermes-etal-2016-royal
%X We present the Royal Society Corpus (RSC) built from the Philosophical Transactions and Proceedings of the Royal Society of London. At present, the corpus contains articles from the first two centuries of the journal (1665―1869) and amounts to around 35 million tokens. The motivation for building the RSC is to investigate the diachronic linguistic development of scientific English. Specifically, we assume that due to specialization, linguistic encodings become more compact over time (Halliday, 1988; Halliday and Martin, 1993), thus creating a specific discourse type characterized by high information density that is functional for expert communication. When building corpora from uncharted material, typically not all relevant meta-data (e.g. author, time, genre) or linguistic data (e.g. sentence/word boundaries, words, parts of speech) is readily available. We present an approach to obtain good quality meta-data and base text data adopting the concept of Agile Software Development.
%U https://aclanthology.org/L16-1305
%P 1928-1931
Markdown (Informal)
[The Royal Society Corpus: From Uncharted Data to Corpus](https://aclanthology.org/L16-1305) (Kermes et al., LREC 2016)
ACL
- Hannah Kermes, Stefania Degaetano-Ortlieb, Ashraf Khamis, Jörg Knappen, and Elke Teich. 2016. The Royal Society Corpus: From Uncharted Data to Corpus. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 1928–1931, Portorož, Slovenia. European Language Resources Association (ELRA).