@inproceedings{bestgen-2022-comparing,
title = "Comparing Formulaic Language in Human and Machine Translation: Insight from a Parliamentary Corpus",
author = "Bestgen, Yves",
editor = "Fi{\v{s}}er, Darja and
Eskevich, Maria and
Lenardi{\v{c}}, Jakob and
de Jong, Franciska",
booktitle = "Proceedings of the Workshop ParlaCLARIN III within the 13th Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.parlaclarin-1.14/",
pages = "101--106",
abstract = "A recent study has shown that, compared to human translations, neural machine translations contain more strongly-associated formulaic sequences made of relatively high-frequency words, but far less strongly-associated formulaic sequences made of relatively rare words. These results were obtained on the basis of translations of quality newspaper articles in which human translations can be thought to be not very literal. The present study attempts to replicate this research using a parliamentary corpus. The results confirm the observations on the news corpus, but the differences are less strong. They suggest that the use of text genres that usually result in more literal translations, such as parliamentary corpora, might be preferable when comparing human and machine translations."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bestgen-2022-comparing">
<titleInfo>
<title>Comparing Formulaic Language in Human and Machine Translation: Insight from a Parliamentary Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yves</namePart>
<namePart type="family">Bestgen</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 Workshop ParlaCLARIN III within the 13th Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Darja</namePart>
<namePart type="family">Fišer</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">Jakob</namePart>
<namePart type="family">Lenardič</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Franciska</namePart>
<namePart type="family">de Jong</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>A recent study has shown that, compared to human translations, neural machine translations contain more strongly-associated formulaic sequences made of relatively high-frequency words, but far less strongly-associated formulaic sequences made of relatively rare words. These results were obtained on the basis of translations of quality newspaper articles in which human translations can be thought to be not very literal. The present study attempts to replicate this research using a parliamentary corpus. The results confirm the observations on the news corpus, but the differences are less strong. They suggest that the use of text genres that usually result in more literal translations, such as parliamentary corpora, might be preferable when comparing human and machine translations.</abstract>
<identifier type="citekey">bestgen-2022-comparing</identifier>
<location>
<url>https://aclanthology.org/2022.parlaclarin-1.14/</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>101</start>
<end>106</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Comparing Formulaic Language in Human and Machine Translation: Insight from a Parliamentary Corpus
%A Bestgen, Yves
%Y Fišer, Darja
%Y Eskevich, Maria
%Y Lenardič, Jakob
%Y de Jong, Franciska
%S Proceedings of the Workshop ParlaCLARIN III within the 13th Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F bestgen-2022-comparing
%X A recent study has shown that, compared to human translations, neural machine translations contain more strongly-associated formulaic sequences made of relatively high-frequency words, but far less strongly-associated formulaic sequences made of relatively rare words. These results were obtained on the basis of translations of quality newspaper articles in which human translations can be thought to be not very literal. The present study attempts to replicate this research using a parliamentary corpus. The results confirm the observations on the news corpus, but the differences are less strong. They suggest that the use of text genres that usually result in more literal translations, such as parliamentary corpora, might be preferable when comparing human and machine translations.
%U https://aclanthology.org/2022.parlaclarin-1.14/
%P 101-106
Markdown (Informal)
[Comparing Formulaic Language in Human and Machine Translation: Insight from a Parliamentary Corpus](https://aclanthology.org/2022.parlaclarin-1.14/) (Bestgen, ParlaCLARIN 2022)
ACL