<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="petit-corro-2023-graph">
    <titleInfo>
        <title>On Graph-based Reentrancy-free Semantic Parsing</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Alban</namePart>
        <namePart type="family">Petit</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Caio</namePart>
        <namePart type="family">Corro</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Transactions of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>MIT Press</publisher>
            <place>
                <placeTerm type="text">Cambridge, MA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>We propose a novel graph-based approach for semantic parsing that resolves two problems observed in the literature: (1) seq2seq models fail on compositional generalization tasks; (2) previous work using phrase structure parsers cannot cover all the semantic parses observed in treebanks. We prove that both MAP inference and latent tag anchoring (required for weakly-supervised learning) are NP-hard problems. We propose two optimization algorithms based on constraint smoothing and conditional gradient to approximately solve these inference problems. Experimentally, our approach delivers state-of-the-art results on GeoQuery, Scan, and Clevr, both for i.i.d. splits and for splits that test for compositional generalization.</abstract>
    <identifier type="citekey">petit-corro-2023-graph</identifier>
    <identifier type="doi">10.1162/tacl_a_00570</identifier>
    <location>
        <url>https://aclanthology.org/2023.tacl-1.41</url>
    </location>
    <part>
        <date>2023</date>
        <detail type="volume"><number>11</number></detail>
        <extent unit="page">
            <start>703</start>
            <end>722</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T On Graph-based Reentrancy-free Semantic Parsing
%A Petit, Alban
%A Corro, Caio
%J Transactions of the Association for Computational Linguistics
%D 2023
%V 11
%I MIT Press
%C Cambridge, MA
%F petit-corro-2023-graph
%X We propose a novel graph-based approach for semantic parsing that resolves two problems observed in the literature: (1) seq2seq models fail on compositional generalization tasks; (2) previous work using phrase structure parsers cannot cover all the semantic parses observed in treebanks. We prove that both MAP inference and latent tag anchoring (required for weakly-supervised learning) are NP-hard problems. We propose two optimization algorithms based on constraint smoothing and conditional gradient to approximately solve these inference problems. Experimentally, our approach delivers state-of-the-art results on GeoQuery, Scan, and Clevr, both for i.i.d. splits and for splits that test for compositional generalization.
%R 10.1162/tacl_a_00570
%U https://aclanthology.org/2023.tacl-1.41
%U https://doi.org/10.1162/tacl_a_00570
%P 703-722

Markdown (Informal)

[On Graph-based Reentrancy-free Semantic Parsing](https://aclanthology.org/2023.tacl-1.41) (Petit & Corro, TACL 2023)

• On Graph-based Reentrancy-free Semantic Parsing (Petit & Corro, TACL 2023)

ACL

• Alban Petit and Caio Corro. 2023. On Graph-based Reentrancy-free Semantic Parsing. Transactions of the Association for Computational Linguistics, 11:703–722.