@inproceedings{menzel-2024-exploring,
title = "Exploring Word Formation Trends in Written, Spoken, Translated and Interpreted {E}uropean Parliament Data {--} A Case Study on Initialisms in {E}nglish and {G}erman",
author = "Menzel, Katrin",
editor = "Fiser, Darja and
Eskevich, Maria and
Bordon, David",
booktitle = "Proceedings of the IV Workshop on Creating, Analysing, and Increasing Accessibility of Parliamentary Corpora (ParlaCLARIN) @ LREC-COLING 2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.parlaclarin-1.9",
pages = "57--65",
abstract = "This paper demonstrates the research potential of a unique European Parliament dataset for register studies, contrastive linguistics, translation and interpreting studies. The dataset consists of parallel data for several European languages, including written source texts and their translations as well as spoken source texts and the transcripts of their simultaneously interpreted versions. The paper presents a cross-linguistic, corpus-based case study on a word formation phenomenon in these European Parliament data that are enriched with various linguistic annotations and metadata as well as with information-theoretic surprisal scores. It addresses the questions of how initialisms are used across languages and production modes in the English and German corpus sections of these European Parliament data, whether there is a correlation between the use of initialisms and the use of their corresponding multiword full forms in the analysed corpus sections and what insights on the informativity and possible processing difficulties of initialisms we can gain from an analysis of information-theoretic surprisal values. The results show that English written originals and German translations are the corpus sections with the highest frequencies of initialisms. The majority of cross-language transfer situations lead to fewer initialisms in the target texts than in the source texts. In the English data, there is a positive correlation between the frequency of initialisms and the frequency of the respective full forms. There is a similar correlation in the German data, apart from the interpreted data. Additionally, the results show that initialisms represent peaks of information with regard to their surprisal values within their segments. Particularly the German data show higher surprisal values of initialisms in mediated language than in non-mediated discourse types, which indicates that in German mediated discourse, initialisms tend to be used in less conventionalised textual contexts than in English.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="menzel-2024-exploring">
<titleInfo>
<title>Exploring Word Formation Trends in Written, Spoken, Translated and Interpreted European Parliament Data – A Case Study on Initialisms in English and German</title>
</titleInfo>
<name type="personal">
<namePart type="given">Katrin</namePart>
<namePart type="family">Menzel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the IV Workshop on Creating, Analysing, and Increasing Accessibility of Parliamentary Corpora (ParlaCLARIN) @ LREC-COLING 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Darja</namePart>
<namePart type="family">Fiser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Eskevich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Bordon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper demonstrates the research potential of a unique European Parliament dataset for register studies, contrastive linguistics, translation and interpreting studies. The dataset consists of parallel data for several European languages, including written source texts and their translations as well as spoken source texts and the transcripts of their simultaneously interpreted versions. The paper presents a cross-linguistic, corpus-based case study on a word formation phenomenon in these European Parliament data that are enriched with various linguistic annotations and metadata as well as with information-theoretic surprisal scores. It addresses the questions of how initialisms are used across languages and production modes in the English and German corpus sections of these European Parliament data, whether there is a correlation between the use of initialisms and the use of their corresponding multiword full forms in the analysed corpus sections and what insights on the informativity and possible processing difficulties of initialisms we can gain from an analysis of information-theoretic surprisal values. The results show that English written originals and German translations are the corpus sections with the highest frequencies of initialisms. The majority of cross-language transfer situations lead to fewer initialisms in the target texts than in the source texts. In the English data, there is a positive correlation between the frequency of initialisms and the frequency of the respective full forms. There is a similar correlation in the German data, apart from the interpreted data. Additionally, the results show that initialisms represent peaks of information with regard to their surprisal values within their segments. Particularly the German data show higher surprisal values of initialisms in mediated language than in non-mediated discourse types, which indicates that in German mediated discourse, initialisms tend to be used in less conventionalised textual contexts than in English.</abstract>
<identifier type="citekey">menzel-2024-exploring</identifier>
<location>
<url>https://aclanthology.org/2024.parlaclarin-1.9</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>57</start>
<end>65</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploring Word Formation Trends in Written, Spoken, Translated and Interpreted European Parliament Data – A Case Study on Initialisms in English and German
%A Menzel, Katrin
%Y Fiser, Darja
%Y Eskevich, Maria
%Y Bordon, David
%S Proceedings of the IV Workshop on Creating, Analysing, and Increasing Accessibility of Parliamentary Corpora (ParlaCLARIN) @ LREC-COLING 2024
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F menzel-2024-exploring
%X This paper demonstrates the research potential of a unique European Parliament dataset for register studies, contrastive linguistics, translation and interpreting studies. The dataset consists of parallel data for several European languages, including written source texts and their translations as well as spoken source texts and the transcripts of their simultaneously interpreted versions. The paper presents a cross-linguistic, corpus-based case study on a word formation phenomenon in these European Parliament data that are enriched with various linguistic annotations and metadata as well as with information-theoretic surprisal scores. It addresses the questions of how initialisms are used across languages and production modes in the English and German corpus sections of these European Parliament data, whether there is a correlation between the use of initialisms and the use of their corresponding multiword full forms in the analysed corpus sections and what insights on the informativity and possible processing difficulties of initialisms we can gain from an analysis of information-theoretic surprisal values. The results show that English written originals and German translations are the corpus sections with the highest frequencies of initialisms. The majority of cross-language transfer situations lead to fewer initialisms in the target texts than in the source texts. In the English data, there is a positive correlation between the frequency of initialisms and the frequency of the respective full forms. There is a similar correlation in the German data, apart from the interpreted data. Additionally, the results show that initialisms represent peaks of information with regard to their surprisal values within their segments. Particularly the German data show higher surprisal values of initialisms in mediated language than in non-mediated discourse types, which indicates that in German mediated discourse, initialisms tend to be used in less conventionalised textual contexts than in English.
%U https://aclanthology.org/2024.parlaclarin-1.9
%P 57-65
Markdown (Informal)
[Exploring Word Formation Trends in Written, Spoken, Translated and Interpreted European Parliament Data – A Case Study on Initialisms in English and German](https://aclanthology.org/2024.parlaclarin-1.9) (Menzel, ParlaCLARIN-WS 2024)
ACL