@inproceedings{nishimura-etal-2025-improving,
title = "Improving {J}apanese-{E}nglish Patent Claim Translation with Clause Segmentation Models based on Word Alignment",
author = "Nishimura, Masato and
Buma, Kosei and
Utsuro, Takehito and
Nagata, Masaaki",
editor = "Bouillon, Pierrette and
Gerlach, Johanna and
Girletti, Sabrina and
Volkart, Lise and
Rubino, Raphael and
Sennrich, Rico and
Farinha, Ana C. and
Gaido, Marco and
Daems, Joke and
Kenny, Dorothy and
Moniz, Helena and
Szoc, Sara",
booktitle = "Proceedings of Machine Translation Summit XX: Volume 1",
month = jun,
year = "2025",
address = "Geneva, Switzerland",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2025.mtsummit-1.25/",
pages = "333--343",
ISBN = "978-2-9701897-0-1",
abstract = "In patent documents, patent claims represent a particularly important section as they define the scope of the claims. However, due to the length and unique formatting of these sentences, neural machine translation (NMT) systems are prone to translation errors, such as omissions and repetitions. To address these challenges, this study proposes a translation method that first segments the source sentences into multiple shorter clauses using a clause segmentation model tailored to facilitate translation. These segmented clauses are then translated using a clause translation model specialized for clause-level translation. Finally, the translated clauses are rearranged and edited into the final translation using a reordering and editing model. In addition, this study proposes a method for constructing clause-level parallel corpora required for training the clause segmentation and clause translation models. This method leverages word alignment tools to create clause-level data from sentence-level parallel corpora. Experimental results demonstrate that the proposed method achieves statistically significant improvements in BLEU scores compared to conventional NMT models. Furthermore, for sentences where conventional NMT models exhibit omissions and repetitions, the proposed method effectively suppresses these errors, enabling more accurate translations."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nishimura-etal-2025-improving">
<titleInfo>
<title>Improving Japanese-English Patent Claim Translation with Clause Segmentation Models based on Word Alignment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Masato</namePart>
<namePart type="family">Nishimura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kosei</namePart>
<namePart type="family">Buma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Takehito</namePart>
<namePart type="family">Utsuro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masaaki</namePart>
<namePart type="family">Nagata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of Machine Translation Summit XX: Volume 1</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pierrette</namePart>
<namePart type="family">Bouillon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johanna</namePart>
<namePart type="family">Gerlach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sabrina</namePart>
<namePart type="family">Girletti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lise</namePart>
<namePart type="family">Volkart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raphael</namePart>
<namePart type="family">Rubino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rico</namePart>
<namePart type="family">Sennrich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ana</namePart>
<namePart type="given">C</namePart>
<namePart type="family">Farinha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Gaido</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joke</namePart>
<namePart type="family">Daems</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dorothy</namePart>
<namePart type="family">Kenny</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Moniz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Szoc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Association for Machine Translation</publisher>
<place>
<placeTerm type="text">Geneva, Switzerland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">978-2-9701897-0-1</identifier>
</relatedItem>
<abstract>In patent documents, patent claims represent a particularly important section as they define the scope of the claims. However, due to the length and unique formatting of these sentences, neural machine translation (NMT) systems are prone to translation errors, such as omissions and repetitions. To address these challenges, this study proposes a translation method that first segments the source sentences into multiple shorter clauses using a clause segmentation model tailored to facilitate translation. These segmented clauses are then translated using a clause translation model specialized for clause-level translation. Finally, the translated clauses are rearranged and edited into the final translation using a reordering and editing model. In addition, this study proposes a method for constructing clause-level parallel corpora required for training the clause segmentation and clause translation models. This method leverages word alignment tools to create clause-level data from sentence-level parallel corpora. Experimental results demonstrate that the proposed method achieves statistically significant improvements in BLEU scores compared to conventional NMT models. Furthermore, for sentences where conventional NMT models exhibit omissions and repetitions, the proposed method effectively suppresses these errors, enabling more accurate translations.</abstract>
<identifier type="citekey">nishimura-etal-2025-improving</identifier>
<location>
<url>https://aclanthology.org/2025.mtsummit-1.25/</url>
</location>
<part>
<date>2025-06</date>
<extent unit="page">
<start>333</start>
<end>343</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Japanese-English Patent Claim Translation with Clause Segmentation Models based on Word Alignment
%A Nishimura, Masato
%A Buma, Kosei
%A Utsuro, Takehito
%A Nagata, Masaaki
%Y Bouillon, Pierrette
%Y Gerlach, Johanna
%Y Girletti, Sabrina
%Y Volkart, Lise
%Y Rubino, Raphael
%Y Sennrich, Rico
%Y Farinha, Ana C.
%Y Gaido, Marco
%Y Daems, Joke
%Y Kenny, Dorothy
%Y Moniz, Helena
%Y Szoc, Sara
%S Proceedings of Machine Translation Summit XX: Volume 1
%D 2025
%8 June
%I European Association for Machine Translation
%C Geneva, Switzerland
%@ 978-2-9701897-0-1
%F nishimura-etal-2025-improving
%X In patent documents, patent claims represent a particularly important section as they define the scope of the claims. However, due to the length and unique formatting of these sentences, neural machine translation (NMT) systems are prone to translation errors, such as omissions and repetitions. To address these challenges, this study proposes a translation method that first segments the source sentences into multiple shorter clauses using a clause segmentation model tailored to facilitate translation. These segmented clauses are then translated using a clause translation model specialized for clause-level translation. Finally, the translated clauses are rearranged and edited into the final translation using a reordering and editing model. In addition, this study proposes a method for constructing clause-level parallel corpora required for training the clause segmentation and clause translation models. This method leverages word alignment tools to create clause-level data from sentence-level parallel corpora. Experimental results demonstrate that the proposed method achieves statistically significant improvements in BLEU scores compared to conventional NMT models. Furthermore, for sentences where conventional NMT models exhibit omissions and repetitions, the proposed method effectively suppresses these errors, enabling more accurate translations.
%U https://aclanthology.org/2025.mtsummit-1.25/
%P 333-343
Markdown (Informal)
[Improving Japanese-English Patent Claim Translation with Clause Segmentation Models based on Word Alignment](https://aclanthology.org/2025.mtsummit-1.25/) (Nishimura et al., MTSummit 2025)
ACL