Investigating the Impact of Different Graph Representations for Relation Extraction with Graph Neural Networks
Blum M, Nolano G, Ell B, Cimiano P (2024)
In: Proceedings of the Deep Learning and Linguistic Linked Data Workshop at LREC-COLING.
Konferenzbeitrag | Englisch
Download
Es wurden keine Dateien hochgeladen. Nur Publikationsnachweis!
Autor*in
Einrichtung
Abstract / Bemerkung
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 in F1.
Erscheinungsjahr
2024
Titel des Konferenzbandes
Proceedings of the Deep Learning and Linguistic Linked Data Workshop at LREC-COLING
Konferenz
Deep Learning and Linguistic Linked Data Workshop at LREC-COLING
Konferenzort
Turin
Konferenzdatum
2024-05-21 – 2024-05-21
Page URI
https://pub.uni-bielefeld.de/record/2988690
Zitieren
Blum M, Nolano G, Ell B, Cimiano P. Investigating the Impact of Different Graph Representations for Relation Extraction with Graph Neural Networks. In: Proceedings of the Deep Learning and Linguistic Linked Data Workshop at LREC-COLING. 2024.
Blum, M., Nolano, G., Ell, B., & Cimiano, P. (2024). Investigating the Impact of Different Graph Representations for Relation Extraction with Graph Neural Networks. Proceedings of the Deep Learning and Linguistic Linked Data Workshop at LREC-COLING
Blum, Moritz, Nolano, Gennaro, Ell, Basil, and Cimiano, Philipp. 2024. “Investigating the Impact of Different Graph Representations for Relation Extraction with Graph Neural Networks”. In Proceedings of the Deep Learning and Linguistic Linked Data Workshop at LREC-COLING.
Blum, M., Nolano, G., Ell, B., and Cimiano, P. (2024). “Investigating the Impact of Different Graph Representations for Relation Extraction with Graph Neural Networks” in Proceedings of the Deep Learning and Linguistic Linked Data Workshop at LREC-COLING.
Blum, M., et al., 2024. Investigating the Impact of Different Graph Representations for Relation Extraction with Graph Neural Networks. In Proceedings of the Deep Learning and Linguistic Linked Data Workshop at LREC-COLING.
M. Blum, et al., “Investigating the Impact of Different Graph Representations for Relation Extraction with Graph Neural Networks”, Proceedings of the Deep Learning and Linguistic Linked Data Workshop at LREC-COLING, 2024.
Blum, M., Nolano, G., Ell, B., Cimiano, P.: Investigating the Impact of Different Graph Representations for Relation Extraction with Graph Neural Networks. Proceedings of the Deep Learning and Linguistic Linked Data Workshop at LREC-COLING. (2024).
Blum, Moritz, Nolano, Gennaro, Ell, Basil, and Cimiano, Philipp. “Investigating the Impact of Different Graph Representations for Relation Extraction with Graph Neural Networks”. Proceedings of the Deep Learning and Linguistic Linked Data Workshop at LREC-COLING. 2024.
Link(s) zu Volltext(en)
Access Level
Open Access