<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2025-neural">
    <titleInfo>
        <title>Neural Semantic Parsing with Extremely Rich Symbolic Meaning Representations</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Xiao</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Gosse</namePart>
        <namePart type="family">Bouma</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Johan</namePart>
        <namePart type="family">Bos</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-03</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>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>Current open-domain neural semantics parsers show impressive performance. However, closer inspection of the symbolic meaning representations they produce reveals significant weaknesses: Sometimes they tend to merely copy character sequences from the source text to form symbolic concepts, defaulting to the most frequent word sense based in the training distribution. By leveraging the hierarchical structure of a lexical ontology, we introduce a novel compositional symbolic representation for concepts based on their position in the taxonomical hierarchy. This representation provides richer semantic information and enhances interpretability. We introduce a neural “taxonomical” semantic parser to utilize this new representation system of predicates, and compare it with a standard neural semantic parser trained on the traditional meaning representation format, employing a novel challenge set and evaluation metric for evaluation. Our experimental findings demonstrate that the taxonomical model, trained on much richer and complex meaning representations, is slightly subordinate in performance to the traditional model using the standard metrics for evaluation, but outperforms it when dealing with out-of-vocabulary concepts. We further show through neural model probing that training on a taxonomic representation enhances the model‘s ability to learn the taxonomical hierarchy. This finding is encouraging for research in computational semantics that aims to combine data-driven distributional meanings with knowledge-based symbolic representations.</abstract>
    <identifier type="citekey">zhang-etal-2025-neural</identifier>
    <identifier type="doi">10.1162/coli_a_00542</identifier>
    <location>
        <url>https://aclanthology.org/2025.cl-1.7/</url>
    </location>
    <part>
        <date>2025-03</date>
        <detail type="volume"><number>51</number></detail>
        <detail type="issue"><number>1</number></detail>
        <extent unit="page">
            <start>235</start>
            <end>274</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Neural Semantic Parsing with Extremely Rich Symbolic Meaning Representations
%A Zhang, Xiao
%A Bouma, Gosse
%A Bos, Johan
%J Computational Linguistics
%D 2025
%8 March
%V 51
%N 1
%I MIT Press
%C Cambridge, MA
%F zhang-etal-2025-neural
%X Current open-domain neural semantics parsers show impressive performance. However, closer inspection of the symbolic meaning representations they produce reveals significant weaknesses: Sometimes they tend to merely copy character sequences from the source text to form symbolic concepts, defaulting to the most frequent word sense based in the training distribution. By leveraging the hierarchical structure of a lexical ontology, we introduce a novel compositional symbolic representation for concepts based on their position in the taxonomical hierarchy. This representation provides richer semantic information and enhances interpretability. We introduce a neural “taxonomical” semantic parser to utilize this new representation system of predicates, and compare it with a standard neural semantic parser trained on the traditional meaning representation format, employing a novel challenge set and evaluation metric for evaluation. Our experimental findings demonstrate that the taxonomical model, trained on much richer and complex meaning representations, is slightly subordinate in performance to the traditional model using the standard metrics for evaluation, but outperforms it when dealing with out-of-vocabulary concepts. We further show through neural model probing that training on a taxonomic representation enhances the model‘s ability to learn the taxonomical hierarchy. This finding is encouraging for research in computational semantics that aims to combine data-driven distributional meanings with knowledge-based symbolic representations.
%R 10.1162/coli_a_00542
%U https://aclanthology.org/2025.cl-1.7/
%U https://doi.org/10.1162/coli_a_00542
%P 235-274

Markdown (Informal)

[Neural Semantic Parsing with Extremely Rich Symbolic Meaning Representations](https://aclanthology.org/2025.cl-1.7/) (Zhang et al., CL 2025)

• Neural Semantic Parsing with Extremely Rich Symbolic Meaning Representations (Zhang et al., CL 2025)

ACL

• Xiao Zhang, Gosse Bouma, and Johan Bos. 2025. Neural Semantic Parsing with Extremely Rich Symbolic Meaning Representations. Computational Linguistics, 51(1):235–274.