Inproceedings3571: Unterschied zwischen den Versionen
Qz7954 (Diskussion | Beiträge) (Die Seite wurde neu angelegt: „{{Publikation Erster Autor |ErsterAutorNachname=Thoma |ErsterAutorVorname=Steffen }} {{Publikation Author |Rank=2 |Author=Achim Rettinger }} {{Publikation Author …“) |
Qz7954 (Diskussion | Beiträge) |
||
| Zeile 12: | Zeile 12: | ||
}} | }} | ||
{{Inproceedings | {{Inproceedings | ||
| − | |Referiert= | + | |Referiert=True |
|Title=Towards Holistic Concept Representations: Embedding Relational Knowledge, Visual Attributes, and Distributional Word Semantics | |Title=Towards Holistic Concept Representations: Embedding Relational Knowledge, Visual Attributes, and Distributional Word Semantics | ||
|Year=2017 | |Year=2017 | ||
|Month=Oktober | |Month=Oktober | ||
| − | |Booktitle= The Semantic Web – ISWC 2017 | + | |Booktitle=The Semantic Web – ISWC 2017 |
|Publisher=Springer | |Publisher=Springer | ||
}} | }} | ||
{{Publikation Details | {{Publikation Details | ||
|Abstract=KnowledgeGraphs(KGs)effectivelycaptureexplicitrelationalknowl- edge about individual entities. However, visual attributes of those entities, like their shape and color and pragmatic aspects concerning their usage in natural lan- guage are not covered. Recent approaches encode such knowledge by learning la- tent representations (‘embeddings’) separately: In computer vision, visual object features are learned from large image collections and in computational linguistics, word embeddings are extracted from huge text corpora which capture their distri- butional semantics. We investigate the potential of complementing the relational knowledge captured in KG embeddings with knowledge from text documents and images by learning a shared latent representation that integrates information across those modalities. Our empirical results show that a joined concept rep- resentation provides measurable benefits for i) semantic similarity benchmarks, since it shows a higher correlation with the human notion of similarity than uni- or bi-modal representations, and ii) entity-type prediction tasks, since it clearly outperforms plain KG embeddings. These findings encourage further research towards capturing types of knowledge that go beyond today’s KGs. | |Abstract=KnowledgeGraphs(KGs)effectivelycaptureexplicitrelationalknowl- edge about individual entities. However, visual attributes of those entities, like their shape and color and pragmatic aspects concerning their usage in natural lan- guage are not covered. Recent approaches encode such knowledge by learning la- tent representations (‘embeddings’) separately: In computer vision, visual object features are learned from large image collections and in computational linguistics, word embeddings are extracted from huge text corpora which capture their distri- butional semantics. We investigate the potential of complementing the relational knowledge captured in KG embeddings with knowledge from text documents and images by learning a shared latent representation that integrates information across those modalities. Our empirical results show that a joined concept rep- resentation provides measurable benefits for i) semantic similarity benchmarks, since it shows a higher correlation with the human notion of similarity than uni- or bi-modal representations, and ii) entity-type prediction tasks, since it clearly outperforms plain KG embeddings. These findings encourage further research towards capturing types of knowledge that go beyond today’s KGs. | ||
| − | |Download=Towards Holistic Concept Representations.pdf, | + | |Download=Towards Holistic Concept Representations.pdf, |
|Forschungsgruppe=Web Science | |Forschungsgruppe=Web Science | ||
}} | }} | ||
Version vom 28. Juli 2017, 09:44 Uhr
Towards Holistic Concept Representations: Embedding Relational Knowledge, Visual Attributes, and Distributional Word Semantics
Towards Holistic Concept Representations: Embedding Relational Knowledge, Visual Attributes, and Distributional Word Semantics
Published: 2017
Oktober
Buchtitel: The Semantic Web – ISWC 2017
Verlag: Springer
Referierte Veröffentlichung
BibTeX
Kurzfassung
KnowledgeGraphs(KGs)effectivelycaptureexplicitrelationalknowl- edge about individual entities. However, visual attributes of those entities, like their shape and color and pragmatic aspects concerning their usage in natural lan- guage are not covered. Recent approaches encode such knowledge by learning la- tent representations (‘embeddings’) separately: In computer vision, visual object features are learned from large image collections and in computational linguistics, word embeddings are extracted from huge text corpora which capture their distri- butional semantics. We investigate the potential of complementing the relational knowledge captured in KG embeddings with knowledge from text documents and images by learning a shared latent representation that integrates information across those modalities. Our empirical results show that a joined concept rep- resentation provides measurable benefits for i) semantic similarity benchmarks, since it shows a higher correlation with the human notion of similarity than uni- or bi-modal representations, and ii) entity-type prediction tasks, since it clearly outperforms plain KG embeddings. These findings encourage further research towards capturing types of knowledge that go beyond today’s KGs.
Download: Media:Towards Holistic Concept Representations.pdf