<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2026-sasu">
    <titleInfo>
        <title>SASU: Structure-Anchored Semantic Unification for Code Search</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Qian</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hao</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hao</namePart>
        <namePart type="family">Jiang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yue</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ruifeng</namePart>
            <namePart type="family">Xu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ayu</namePart>
            <namePart type="family">Purwarianti</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tong</namePart>
            <namePart type="family">Rong</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jun</namePart>
            <namePart type="family">Suzuki</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Hengqin, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-444-6</identifier>
    </relatedItem>
    <abstract>Code search aims to retrieve code snippets according to natural-language intent. Despite the progress of pretrained code models, there remains a gap between natural language and programming language: descriptions are usually sequential and lexical, while code is governed by syntax, data dependencies, and execution logic. Existing retrieval models often rely on token-level matching or use structure as auxiliary information, which limits their ability to capture executable behavior under lexical variation or incomplete code evidence. In this paper, we propose SASU, a structure-anchored semantic unification framework for code search. SASU extracts a normalized multi-relational graph for each function and composes syntax, data-flow, control-flow, call, return, and exception relations into a unified structural view. The structural representation is then used to guide node-level lexical evidence selection before code and text are aligned in the same retrieval space. Experiments on CodeSearchNet show that SASU achieves 0.835 MRR for code-to-text retrieval and 0.840 MRR for text-to-code retrieval across Python, Java, and JavaScript. Under 40–60% node deletion, SASU retains 86.6% of its full-graph MRR, indicating that structure provides useful retrieval signals beyond lexical pretraining.</abstract>
    <identifier type="citekey">zhang-etal-2026-sasu</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-aacl.187/</url>
    </location>
    <part>
        <date>2026-11</date>
        <extent unit="page">
            <start>3724</start>
            <end>3735</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T SASU: Structure-Anchored Semantic Unification for Code Search
%A Zhang, Qian
%A Li, Hao
%A Jiang, Hao
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-444-6
%F zhang-etal-2026-sasu
%X Code search aims to retrieve code snippets according to natural-language intent. Despite the progress of pretrained code models, there remains a gap between natural language and programming language: descriptions are usually sequential and lexical, while code is governed by syntax, data dependencies, and execution logic. Existing retrieval models often rely on token-level matching or use structure as auxiliary information, which limits their ability to capture executable behavior under lexical variation or incomplete code evidence. In this paper, we propose SASU, a structure-anchored semantic unification framework for code search. SASU extracts a normalized multi-relational graph for each function and composes syntax, data-flow, control-flow, call, return, and exception relations into a unified structural view. The structural representation is then used to guide node-level lexical evidence selection before code and text are aligned in the same retrieval space. Experiments on CodeSearchNet show that SASU achieves 0.835 MRR for code-to-text retrieval and 0.840 MRR for text-to-code retrieval across Python, Java, and JavaScript. Under 40–60% node deletion, SASU retains 86.6% of its full-graph MRR, indicating that structure provides useful retrieval signals beyond lexical pretraining.
%U https://aclanthology.org/2026.findings-aacl.187/
%P 3724-3735

Markdown (Informal)

[SASU: Structure-Anchored Semantic Unification for Code Search](https://aclanthology.org/2026.findings-aacl.187/) (Zhang et al., Findings 2026)

• SASU: Structure-Anchored Semantic Unification for Code Search (Zhang et al., Findings 2026)

ACL

• Qian Zhang, Hao Li, and Hao Jiang. 2026. SASU: Structure-Anchored Semantic Unification for Code Search. In Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026, pages 3724–3735, Hengqin, China. Association for Computational Linguistics.