DynaSemble: Dynamic Ensembling of Textual and Structure-Based Models for Knowledge Graph Completion

Ananjan Nandi, Navdeep Kaur, Parag Singla, Mausam .


Abstract
We consider two popular approaches to KnowledgeGraph Completion (KGC): textual modelsthat rely on textual entity descriptions, andstructure-based models that exploit the connectivitystructure of the Knowledge Graph(KG). Preliminary experiments show that theseapproaches have complementary strengths:structure-based models perform exceptionallywell when the gold answer is easily reachablefrom the query head in the KG, while textualmodels exploit descriptions to give goodperformance even when the gold answer isnot easily reachable. In response, we proposeDynaSemble, a novel method for learningquery-dependent ensemble weights to combinethese approaches by using the distributions ofscores assigned by the models in the ensembleto all candidate entities. DynaSemble achievesstate-of-the-art results on three standard KGCdatasets, with up to 6.8 pt MRR and 8.3 ptHits@1 gains over the best baseline model forthe WN18RR dataset.
Anthology ID:
2024.acl-short.20
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
205–216
Language:
URL:
https://aclanthology.org/2024.acl-short.20
DOI:
10.18653/v1/2024.acl-short.20
Bibkey:
Cite (ACL):
Ananjan Nandi, Navdeep Kaur, Parag Singla, and Mausam .. 2024. DynaSemble: Dynamic Ensembling of Textual and Structure-Based Models for Knowledge Graph Completion. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 205–216, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
DynaSemble: Dynamic Ensembling of Textual and Structure-Based Models for Knowledge Graph Completion (Nandi et al., ACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.acl-short.20.pdf