<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kasner-etal-2023-mind">
    <titleInfo>
        <title>Mind the Labels: Describing Relations in Knowledge Graphs With Pretrained Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Zdeněk</namePart>
        <namePart type="family">Kasner</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ioannis</namePart>
        <namePart type="family">Konstas</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ondrej</namePart>
        <namePart type="family">Dusek</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Andreas</namePart>
            <namePart type="family">Vlachos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Isabelle</namePart>
            <namePart type="family">Augenstein</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Dubrovnik, Croatia</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Pretrained language models (PLMs) for data-to-text (D2T) generation can use human-readable data labels such as column headings, keys, or relation names to generalize to out-of-domain examples. However, the models are well-known in producing semantically inaccurate outputs if these labels are ambiguous or incomplete, which is often the case in D2T datasets. In this paper, we expose this issue on the task of descibing a relation between two entities. For our experiments, we collect a novel dataset for verbalizing a diverse set of 1,522 unique relations from three large-scale knowledge graphs (Wikidata, DBPedia, YAGO). We find that although PLMs for D2T generation expectedly fail on unclear cases, models trained with a large variety of relation labels are surprisingly robust in verbalizing novel, unseen relations. We argue that using data with a diverse set of clear and meaningful labels is key to training D2T generation systems capable of generalizing to novel domains.</abstract>
    <identifier type="citekey">kasner-etal-2023-mind</identifier>
    <identifier type="doi">10.18653/v1/2023.eacl-main.176</identifier>
    <location>
        <url>https://aclanthology.org/2023.eacl-main.176</url>
    </location>
    <part>
        <date>2023-05</date>
        <extent unit="page">
            <start>2398</start>
            <end>2415</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Mind the Labels: Describing Relations in Knowledge Graphs With Pretrained Models
%A Kasner, Zdeněk
%A Konstas, Ioannis
%A Dusek, Ondrej
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F kasner-etal-2023-mind
%X Pretrained language models (PLMs) for data-to-text (D2T) generation can use human-readable data labels such as column headings, keys, or relation names to generalize to out-of-domain examples. However, the models are well-known in producing semantically inaccurate outputs if these labels are ambiguous or incomplete, which is often the case in D2T datasets. In this paper, we expose this issue on the task of descibing a relation between two entities. For our experiments, we collect a novel dataset for verbalizing a diverse set of 1,522 unique relations from three large-scale knowledge graphs (Wikidata, DBPedia, YAGO). We find that although PLMs for D2T generation expectedly fail on unclear cases, models trained with a large variety of relation labels are surprisingly robust in verbalizing novel, unseen relations. We argue that using data with a diverse set of clear and meaningful labels is key to training D2T generation systems capable of generalizing to novel domains.
%R 10.18653/v1/2023.eacl-main.176
%U https://aclanthology.org/2023.eacl-main.176
%U https://doi.org/10.18653/v1/2023.eacl-main.176
%P 2398-2415

Markdown (Informal)

[Mind the Labels: Describing Relations in Knowledge Graphs With Pretrained Models](https://aclanthology.org/2023.eacl-main.176) (Kasner et al., EACL 2023)

• Mind the Labels: Describing Relations in Knowledge Graphs With Pretrained Models (Kasner et al., EACL 2023)

ACL

• Zdeněk Kasner, Ioannis Konstas, and Ondrej Dusek. 2023. Mind the Labels: Describing Relations in Knowledge Graphs With Pretrained Models. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 2398–2415, Dubrovnik, Croatia. Association for Computational Linguistics.