<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="debenedetto-2024-linearization">
    <titleInfo>
        <title>Linearization Order Matters for AMR-to-Text Generation Input</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Justin</namePart>
        <namePart type="family">DeBenedetto</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-06</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2024 UMR Parsing Workshop</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Nianwen</namePart>
            <namePart type="family">Xue</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">James</namePart>
            <namePart type="family">Martin</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Boulder, Colorado</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Abstract Meaning Representation (AMR) is a semantic graph formalism designed to capture sentence meaning using a directed graph. Many systems treat AMR-to-text generation as a sequence-to-sequence problem, drawing upon existing models. The largest AMR dataset (AMR 3.0) provides a sequence format which is considered equivalent to the graph format. However, due to the position-sensitive nature of sequence-to-sequence models, graph traversal order affects system performance. In this work we explore the effect that different, valid orderings have on the performance of sequence-to-sequence AMR-to-text systems and find that changing the traversal order can result in a BLEU score drop of up to 17.5 on a state-of-the-art system.</abstract>
    <identifier type="citekey">debenedetto-2024-linearization</identifier>
    <location>
        <url>https://aclanthology.org/2024.umrpw-1.1/</url>
    </location>
    <part>
        <date>2024-06</date>
        <extent unit="page">
            <start>1</start>
            <end>7</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Linearization Order Matters for AMR-to-Text Generation Input
%A DeBenedetto, Justin
%Y Xue, Nianwen
%Y Martin, James
%S Proceedings of the 2024 UMR Parsing Workshop
%D 2024
%8 June
%I Association for Computational Linguistics
%C Boulder, Colorado
%F debenedetto-2024-linearization
%X Abstract Meaning Representation (AMR) is a semantic graph formalism designed to capture sentence meaning using a directed graph. Many systems treat AMR-to-text generation as a sequence-to-sequence problem, drawing upon existing models. The largest AMR dataset (AMR 3.0) provides a sequence format which is considered equivalent to the graph format. However, due to the position-sensitive nature of sequence-to-sequence models, graph traversal order affects system performance. In this work we explore the effect that different, valid orderings have on the performance of sequence-to-sequence AMR-to-text systems and find that changing the traversal order can result in a BLEU score drop of up to 17.5 on a state-of-the-art system.
%U https://aclanthology.org/2024.umrpw-1.1/
%P 1-7

Markdown (Informal)

[Linearization Order Matters for AMR-to-Text Generation Input](https://aclanthology.org/2024.umrpw-1.1/) (DeBenedetto, UMRPW 2024)

• Linearization Order Matters for AMR-to-Text Generation Input (DeBenedetto, UMRPW 2024)

ACL

• Justin DeBenedetto. 2024. Linearization Order Matters for AMR-to-Text Generation Input. In Proceedings of the 2024 UMR Parsing Workshop, pages 1–7, Boulder, Colorado. Association for Computational Linguistics.