@inproceedings{nagata-etal-2024-japarapat-large,
title = "{J}a{P}ara{P}at: A Large-Scale {J}apanese-{E}nglish Parallel Patent Application Corpus",
author = "Nagata, Masaaki and
Morishita, Makoto and
Chousa, Katsuki and
Yasuda, Norihito",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.826",
pages = "9452--9462",
abstract = "We constructed JaParaPat (Japanese-English Parallel Patent Application Corpus), a bilingual corpus of more than 300 million Japanese-English sentence pairs from patent applications published in Japan and the United States from 2000 to 2021. We obtained the publication of unexamined patent applications from the Japan Patent Office (JPO) and the United States Patent and Trademark Office (USPTO). We also obtained patent family information from the DOCDB, that is a bibliographic database maintained by the European Patent Office (EPO). We extracted approximately 1.4M Japanese-English document pairs, which are translations of each other based on the patent families, and extracted about 350M sentence pairs from the document pairs using a translation-based sentence alignment method whose initial translation model is bootstrapped from a dictionary-based sentence alignment. We experimentally improved the accuracy of the patent translations by 20 bleu points by adding more than 300M sentence pairs obtained from patent applications to 22M sentence pairs obtained from the web.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nagata-etal-2024-japarapat-large">
<titleInfo>
<title>JaParaPat: A Large-Scale Japanese-English Parallel Patent Application Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Masaaki</namePart>
<namePart type="family">Nagata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Makoto</namePart>
<namePart type="family">Morishita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katsuki</namePart>
<namePart type="family">Chousa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Norihito</namePart>
<namePart type="family">Yasuda</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 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</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">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</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>We constructed JaParaPat (Japanese-English Parallel Patent Application Corpus), a bilingual corpus of more than 300 million Japanese-English sentence pairs from patent applications published in Japan and the United States from 2000 to 2021. We obtained the publication of unexamined patent applications from the Japan Patent Office (JPO) and the United States Patent and Trademark Office (USPTO). We also obtained patent family information from the DOCDB, that is a bibliographic database maintained by the European Patent Office (EPO). We extracted approximately 1.4M Japanese-English document pairs, which are translations of each other based on the patent families, and extracted about 350M sentence pairs from the document pairs using a translation-based sentence alignment method whose initial translation model is bootstrapped from a dictionary-based sentence alignment. We experimentally improved the accuracy of the patent translations by 20 bleu points by adding more than 300M sentence pairs obtained from patent applications to 22M sentence pairs obtained from the web.</abstract>
<identifier type="citekey">nagata-etal-2024-japarapat-large</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.826</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>9452</start>
<end>9462</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T JaParaPat: A Large-Scale Japanese-English Parallel Patent Application Corpus
%A Nagata, Masaaki
%A Morishita, Makoto
%A Chousa, Katsuki
%A Yasuda, Norihito
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F nagata-etal-2024-japarapat-large
%X We constructed JaParaPat (Japanese-English Parallel Patent Application Corpus), a bilingual corpus of more than 300 million Japanese-English sentence pairs from patent applications published in Japan and the United States from 2000 to 2021. We obtained the publication of unexamined patent applications from the Japan Patent Office (JPO) and the United States Patent and Trademark Office (USPTO). We also obtained patent family information from the DOCDB, that is a bibliographic database maintained by the European Patent Office (EPO). We extracted approximately 1.4M Japanese-English document pairs, which are translations of each other based on the patent families, and extracted about 350M sentence pairs from the document pairs using a translation-based sentence alignment method whose initial translation model is bootstrapped from a dictionary-based sentence alignment. We experimentally improved the accuracy of the patent translations by 20 bleu points by adding more than 300M sentence pairs obtained from patent applications to 22M sentence pairs obtained from the web.
%U https://aclanthology.org/2024.lrec-main.826
%P 9452-9462
Markdown (Informal)
[JaParaPat: A Large-Scale Japanese-English Parallel Patent Application Corpus](https://aclanthology.org/2024.lrec-main.826) (Nagata et al., LREC-COLING 2024)
ACL