<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ishimaru-etal-2026-coordinate-structure">
    <titleInfo>
        <title>Coordinate Structure Alignment of Patent Claims by LLMs</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Tsukasa</namePart>
        <namePart type="family">Ishimaru</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>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-462-0</identifier>
    </relatedItem>
    <abstract>This paper proposes an LLM-based method for cross-lingual alignment of coordinate structures in Japanese–English and Chinese–English patent claims. The approach has two components. First, we construct task-specific alignment datasets by translating Penn Treebank-3 English sentences into Japanese and Chinese and projecting coordinate-structure annotations using syntactic parse trees, word alignments, and the GHKM algorithm. Second, we formulate alignment as a TANL-based text generation task in which LLMs generate the target sentence with the corresponding span tagged. Although the training data are derived from a general-domain corpus, evaluation is conducted on manually annotated real patent claims. Across four translation directions, the proposed approach consistently outperforms SpanAlign, an encoder-based alignment baseline built on SQuAD-style cross-lingual span prediction and ILP-based alignment. Controlled analyses show that the TANL formulation improves performance independently of supervised fine-tuning and that automatically generated demonstrations achieve performance close to manually constructed examples in the tested 3-shot setting. Supervised fine-tuning with the automatically constructed datasets further improves open-weight LLMs, with the best fine-tuned model in each direction achieving an F1 score above 0.8.</abstract>
    <identifier type="citekey">ishimaru-etal-2026-coordinate-structure</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.419/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>8830</start>
            <end>8845</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Coordinate Structure Alignment of Patent Claims by LLMs
%A Ishimaru, Tsukasa
%A Utsuro, Takehito
%A Nagata, Masaaki
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F ishimaru-etal-2026-coordinate-structure
%X This paper proposes an LLM-based method for cross-lingual alignment of coordinate structures in Japanese–English and Chinese–English patent claims. The approach has two components. First, we construct task-specific alignment datasets by translating Penn Treebank-3 English sentences into Japanese and Chinese and projecting coordinate-structure annotations using syntactic parse trees, word alignments, and the GHKM algorithm. Second, we formulate alignment as a TANL-based text generation task in which LLMs generate the target sentence with the corresponding span tagged. Although the training data are derived from a general-domain corpus, evaluation is conducted on manually annotated real patent claims. Across four translation directions, the proposed approach consistently outperforms SpanAlign, an encoder-based alignment baseline built on SQuAD-style cross-lingual span prediction and ILP-based alignment. Controlled analyses show that the TANL formulation improves performance independently of supervised fine-tuning and that automatically generated demonstrations achieve performance close to manually constructed examples in the tested 3-shot setting. Supervised fine-tuning with the automatically constructed datasets further improves open-weight LLMs, with the best fine-tuned model in each direction achieving an F1 score above 0.8.
%U https://aclanthology.org/2026.findings-emnlp.419/
%P 8830-8845

Markdown (Informal)

[Coordinate Structure Alignment of Patent Claims by LLMs](https://aclanthology.org/2026.findings-emnlp.419/) (Ishimaru et al., Findings 2026)

• Coordinate Structure Alignment of Patent Claims by LLMs (Ishimaru et al., Findings 2026)

ACL

• Tsukasa Ishimaru, Takehito Utsuro, and Masaaki Nagata. 2026. Coordinate Structure Alignment of Patent Claims by LLMs. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 8830–8845, Budapest, Hungary. Association for Computational Linguistics.