@inproceedings{blum-etal-2024-investigating,
title = "Investigating the Impact of Different Graph Representations for Relation Extraction with Graph Neural Networks",
author = "Blum, Moritz and
Nolano, Gennaro and
Ell, Basil and
Cimiano, Philipp",
editor = "S{\'e}rasset, Gilles and
Oliveira, Hugo Gon{\c{c}}alo and
Oleskeviciene, Giedre Valunaite",
booktitle = "Proceedings of the Workshop on Deep Learning and Linked Data (DLnLD) @ LREC-COLING 2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.dlnld-1.1",
pages = "1--13",
abstract = "Graph Neural Networks(GNNs) have been applied successfully to various NLP tasks, particularly Relation Extraction(RE). Even though most of these approaches rely on the syntactic dependency tree of a sentence to derive a graph representation, the impact of this choice compared to other possible graph representations has not been evaluated. We examine the effect of representing text though a graph of different graph representations for GNNs that are applied to RE, considering, e.g., a fully connected graph of tokens, of semantic role structures, and combinations thereof. We further examine the impact of background knowledge injection from Knowledge Graphs(KGs) into the graph representation to achieve enhanced graph representations. Our results show that combining multiple graph representations can improve the model{'}s predictions. Moreover, the integration of background knowledge positively impacts scores, as enhancing the text graphs with Wikidata features or WordNet features can lead to an improvement of close to 0.1 points in F1.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="blum-etal-2024-investigating">
<titleInfo>
<title>Investigating the Impact of Different Graph Representations for Relation Extraction with Graph Neural Networks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Moritz</namePart>
<namePart type="family">Blum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gennaro</namePart>
<namePart type="family">Nolano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Basil</namePart>
<namePart type="family">Ell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Cimiano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Deep Learning and Linked Data (DLnLD) @ LREC-COLING 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gilles</namePart>
<namePart type="family">Sérasset</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hugo</namePart>
<namePart type="given">Gonçalo</namePart>
<namePart type="family">Oliveira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giedre</namePart>
<namePart type="given">Valunaite</namePart>
<namePart type="family">Oleskeviciene</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Graph Neural Networks(GNNs) have been applied successfully to various NLP tasks, particularly Relation Extraction(RE). Even though most of these approaches rely on the syntactic dependency tree of a sentence to derive a graph representation, the impact of this choice compared to other possible graph representations has not been evaluated. We examine the effect of representing text though a graph of different graph representations for GNNs that are applied to RE, considering, e.g., a fully connected graph of tokens, of semantic role structures, and combinations thereof. We further examine the impact of background knowledge injection from Knowledge Graphs(KGs) into the graph representation to achieve enhanced graph representations. Our results show that combining multiple graph representations can improve the model’s predictions. Moreover, the integration of background knowledge positively impacts scores, as enhancing the text graphs with Wikidata features or WordNet features can lead to an improvement of close to 0.1 points in F1.</abstract>
<identifier type="citekey">blum-etal-2024-investigating</identifier>
<location>
<url>https://aclanthology.org/2024.dlnld-1.1</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>1</start>
<end>13</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Investigating the Impact of Different Graph Representations for Relation Extraction with Graph Neural Networks
%A Blum, Moritz
%A Nolano, Gennaro
%A Ell, Basil
%A Cimiano, Philipp
%Y Sérasset, Gilles
%Y Oliveira, Hugo Gonçalo
%Y Oleskeviciene, Giedre Valunaite
%S Proceedings of the Workshop on Deep Learning and Linked Data (DLnLD) @ LREC-COLING 2024
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F blum-etal-2024-investigating
%X Graph Neural Networks(GNNs) have been applied successfully to various NLP tasks, particularly Relation Extraction(RE). Even though most of these approaches rely on the syntactic dependency tree of a sentence to derive a graph representation, the impact of this choice compared to other possible graph representations has not been evaluated. We examine the effect of representing text though a graph of different graph representations for GNNs that are applied to RE, considering, e.g., a fully connected graph of tokens, of semantic role structures, and combinations thereof. We further examine the impact of background knowledge injection from Knowledge Graphs(KGs) into the graph representation to achieve enhanced graph representations. Our results show that combining multiple graph representations can improve the model’s predictions. Moreover, the integration of background knowledge positively impacts scores, as enhancing the text graphs with Wikidata features or WordNet features can lead to an improvement of close to 0.1 points in F1.
%U https://aclanthology.org/2024.dlnld-1.1
%P 1-13
Markdown (Informal)
[Investigating the Impact of Different Graph Representations for Relation Extraction with Graph Neural Networks](https://aclanthology.org/2024.dlnld-1.1) (Blum et al., DLnLD-WS 2024)
ACL