<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-schubert-2019-type">
    <titleInfo>
        <title>A Type-coherent, Expressive Representation as an Initial Step to Language Understanding</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Gene</namePart>
        <namePart type="given">Louis</namePart>
        <namePart type="family">Kim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lenhart</namePart>
        <namePart type="family">Schubert</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-may</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 13th International Conference on Computational Semantics - Long Papers</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Gothenburg, Sweden</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>A growing interest in tasks involving language understanding by the NLP community has led to the need for effective semantic parsing and inference. Modern NLP systems use semantic representations that do not quite fulfill the nuanced needs for language understanding: adequately modeling language semantics, enabling general inferences, and being accurately recoverable. This document describes underspecified logical forms (ULF) for Episodic Logic (EL), which is an initial form for a semantic representation that balances these needs. ULFs fully resolve the semantic type structure while leaving issues such as quantifier scope, word sense, and anaphora unresolved; they provide a starting point for further resolution into EL, and enable certain structural inferences without further resolution. This document also presents preliminary results of creating a hand-annotated corpus of ULFs for the purpose of training a precise ULF parser, showing a three-person pairwise interannotator agreement of 0.88 on confident annotations. We hypothesize that a divide-and-conquer approach to semantic parsing starting with derivation of ULFs will lead to semantic analyses that do justice to subtle aspects of linguistic meaning, and will enable construction of more accurate semantic parsers.</abstract>
    <identifier type="citekey">kim-schubert-2019-type</identifier>
    <identifier type="doi">10.18653/v1/W19-0402</identifier>
    <location>
        <url>https://aclanthology.org/W19-0402</url>
    </location>
    <part>
        <date>2019-may</date>
        <extent unit="page">
            <start>13</start>
            <end>30</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T A Type-coherent, Expressive Representation as an Initial Step to Language Understanding
%A Kim, Gene Louis
%A Schubert, Lenhart
%S Proceedings of the 13th International Conference on Computational Semantics - Long Papers
%D 2019
%8 may
%I Association for Computational Linguistics
%C Gothenburg, Sweden
%F kim-schubert-2019-type
%X A growing interest in tasks involving language understanding by the NLP community has led to the need for effective semantic parsing and inference. Modern NLP systems use semantic representations that do not quite fulfill the nuanced needs for language understanding: adequately modeling language semantics, enabling general inferences, and being accurately recoverable. This document describes underspecified logical forms (ULF) for Episodic Logic (EL), which is an initial form for a semantic representation that balances these needs. ULFs fully resolve the semantic type structure while leaving issues such as quantifier scope, word sense, and anaphora unresolved; they provide a starting point for further resolution into EL, and enable certain structural inferences without further resolution. This document also presents preliminary results of creating a hand-annotated corpus of ULFs for the purpose of training a precise ULF parser, showing a three-person pairwise interannotator agreement of 0.88 on confident annotations. We hypothesize that a divide-and-conquer approach to semantic parsing starting with derivation of ULFs will lead to semantic analyses that do justice to subtle aspects of linguistic meaning, and will enable construction of more accurate semantic parsers.
%R 10.18653/v1/W19-0402
%U https://aclanthology.org/W19-0402
%U https://doi.org/10.18653/v1/W19-0402
%P 13-30

Markdown (Informal)

[A Type-coherent, Expressive Representation as an Initial Step to Language Understanding](https://aclanthology.org/W19-0402) (Kim & Schubert, 2019)

• A Type-coherent, Expressive Representation as an Initial Step to Language Understanding (Kim & Schubert, 2019)

ACL

• Gene Louis Kim and Lenhart Schubert. 2019. A Type-coherent, Expressive Representation as an Initial Step to Language Understanding. In Proceedings of the 13th International Conference on Computational Semantics - Long Papers, pages 13–30, Gothenburg, Sweden. Association for Computational Linguistics.