@inproceedings{heafield-etal-2022-europat,
title = "The {E}uro{P}at Corpus: A Parallel Corpus of {E}uropean Patent Data",
author = "Heafield, Kenneth and
Farrow, Elaine and
van der Linde, Jelmer and
Ram{\'i}rez-S{\'a}nchez, Gema and
Wiggins, Dion",
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
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.78/",
pages = "732--740",
abstract = "We present the EuroPat corpus of patent-specific parallel data for 6 official European languages paired with English: German, Spanish, French, Croatian, Norwegian, and Polish. The filtered parallel corpora range in size from 51 million sentences (Spanish-English) to 154k sentences (Croatian-English), with the unfiltered (raw) corpora being up to 2 times larger. Access to clean, high quality, parallel data in technical domains such as science, engineering, and medicine is needed for training neural machine translation systems for tasks like online dispute resolution and eProcurement. Our evaluation found that the addition of EuroPat data to a generic baseline improved the performance of machine translation systems on in-domain test data in German, Spanish, French, and Polish; and in translating patent data from Croatian to English. The corpus has been released under Creative Commons Zero, and is expected to be widely useful for training high-quality machine translation systems, and particularly for those targeting technical documents such as patents and contracts."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="heafield-etal-2022-europat">
<titleInfo>
<title>The EuroPat Corpus: A Parallel Corpus of European Patent Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kenneth</namePart>
<namePart type="family">Heafield</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elaine</namePart>
<namePart type="family">Farrow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jelmer</namePart>
<namePart type="family">van der Linde</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gema</namePart>
<namePart type="family">Ramírez-Sánchez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dion</namePart>
<namePart type="family">Wiggins</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 Thirteenth 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">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>
</relatedItem>
<abstract>We present the EuroPat corpus of patent-specific parallel data for 6 official European languages paired with English: German, Spanish, French, Croatian, Norwegian, and Polish. The filtered parallel corpora range in size from 51 million sentences (Spanish-English) to 154k sentences (Croatian-English), with the unfiltered (raw) corpora being up to 2 times larger. Access to clean, high quality, parallel data in technical domains such as science, engineering, and medicine is needed for training neural machine translation systems for tasks like online dispute resolution and eProcurement. Our evaluation found that the addition of EuroPat data to a generic baseline improved the performance of machine translation systems on in-domain test data in German, Spanish, French, and Polish; and in translating patent data from Croatian to English. The corpus has been released under Creative Commons Zero, and is expected to be widely useful for training high-quality machine translation systems, and particularly for those targeting technical documents such as patents and contracts.</abstract>
<identifier type="citekey">heafield-etal-2022-europat</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.78/</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>732</start>
<end>740</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The EuroPat Corpus: A Parallel Corpus of European Patent Data
%A Heafield, Kenneth
%A Farrow, Elaine
%A van der Linde, Jelmer
%A Ramírez-Sánchez, Gema
%A Wiggins, Dion
%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 Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F heafield-etal-2022-europat
%X We present the EuroPat corpus of patent-specific parallel data for 6 official European languages paired with English: German, Spanish, French, Croatian, Norwegian, and Polish. The filtered parallel corpora range in size from 51 million sentences (Spanish-English) to 154k sentences (Croatian-English), with the unfiltered (raw) corpora being up to 2 times larger. Access to clean, high quality, parallel data in technical domains such as science, engineering, and medicine is needed for training neural machine translation systems for tasks like online dispute resolution and eProcurement. Our evaluation found that the addition of EuroPat data to a generic baseline improved the performance of machine translation systems on in-domain test data in German, Spanish, French, and Polish; and in translating patent data from Croatian to English. The corpus has been released under Creative Commons Zero, and is expected to be widely useful for training high-quality machine translation systems, and particularly for those targeting technical documents such as patents and contracts.
%U https://aclanthology.org/2022.lrec-1.78/
%P 732-740
Markdown (Informal)
[The EuroPat Corpus: A Parallel Corpus of European Patent Data](https://aclanthology.org/2022.lrec-1.78/) (Heafield et al., LREC 2022)
ACL
- Kenneth Heafield, Elaine Farrow, Jelmer van der Linde, Gema Ramírez-Sánchez, and Dion Wiggins. 2022. The EuroPat Corpus: A Parallel Corpus of European Patent Data. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 732–740, Marseille, France. European Language Resources Association.