Learning to Borrow– Relation Representation for Without-Mention Entity-Pairs for Knowledge Graph Completion
Huda Hakami, Mona Hakami, Angrosh Mandya, Danushka Bollegala
Abstract
Prior work on integrating text corpora with knowledge graphs (KGs) to improve Knowledge Graph Embedding (KGE) have obtained good performance for entities that co-occur in sentences in text corpora. Such sentences (textual mentions of entity-pairs) are represented as Lexicalised Dependency Paths (LDPs) between two entities. However, it is not possible to represent relations between entities that do not co-occur in a single sentence using LDPs. In this paper, we propose and evaluate several methods to address this problem, where we borrow LDPs from the entity pairs that co-occur in sentences in the corpus (i.e. with mentions entity pairs) to represent entity pairs that do not co-occur in any sentence in the corpus (i.e. without mention entity pairs). We propose a supervised borrowing method, SuperBorrow, that learns to score the suitability of an LDP to represent a without-mentions entity pair using pre-trained entity embeddings and contextualised LDP representations. Experimental results show that SuperBorrow improves the link prediction performance of multiple widely-used prior KGE methods such as TransE, DistMult, ComplEx and RotatE.- Anthology ID:
- 2022.naacl-main.209
- Volume:
- Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
- Month:
- July
- Year:
- 2022
- Address:
- Seattle, United States
- Editors:
- Marine Carpuat, Marie-Catherine de Marneffe, Ivan Vladimir Meza Ruiz
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2887–2898
- Language:
- URL:
- https://aclanthology.org/2022.naacl-main.209
- DOI:
- 10.18653/v1/2022.naacl-main.209
- Cite (ACL):
- Huda Hakami, Mona Hakami, Angrosh Mandya, and Danushka Bollegala. 2022. Learning to Borrow– Relation Representation for Without-Mention Entity-Pairs for Knowledge Graph Completion. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2887–2898, Seattle, United States. Association for Computational Linguistics.
- Cite (Informal):
- Learning to Borrow– Relation Representation for Without-Mention Entity-Pairs for Knowledge Graph Completion (Hakami et al., NAACL 2022)
- PDF:
- https://preview.aclanthology.org/naacl24-info/2022.naacl-main.209.pdf
- Code
- huda-hakami/learning-to-borrow-for-kgs
- Data
- FB15k-237